[llvm] TTI: Fix special casing vectorization costs of saturating add/sub (PR #97463)
Matt Arsenault via llvm-commits
llvm-commits at lists.llvm.org
Thu Jul 25 10:28:10 PDT 2024
https://github.com/arsenm updated https://github.com/llvm/llvm-project/pull/97463
>From 9cda311cc5ef0c6c3181ad94f79cba7b689669ff Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault at amd.com>
Date: Tue, 2 Jul 2024 21:28:30 +0200
Subject: [PATCH 1/5] AMDGPU: Add baseline test for vectorize of integer
min/max
---
.../SLPVectorizer/AMDGPU/min_max.ll | 354 ++++++++++++++++++
1 file changed, 354 insertions(+)
create mode 100644 llvm/test/Transforms/SLPVectorizer/AMDGPU/min_max.ll
diff --git a/llvm/test/Transforms/SLPVectorizer/AMDGPU/min_max.ll b/llvm/test/Transforms/SLPVectorizer/AMDGPU/min_max.ll
new file mode 100644
index 0000000000000..f44705a925d5a
--- /dev/null
+++ b/llvm/test/Transforms/SLPVectorizer/AMDGPU/min_max.ll
@@ -0,0 +1,354 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -mcpu=hawaii -passes=slp-vectorizer,instcombine %s | FileCheck -check-prefixes=GCN,GFX7 %s
+; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -passes=slp-vectorizer,instcombine %s | FileCheck -check-prefixes=GCN,GFX8 %s
+; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -passes=slp-vectorizer,instcombine %s | FileCheck -check-prefixes=GCN,GFX9 %s
+
+define <2 x i16> @uadd_sat_v2i16(<2 x i16> %arg0, <2 x i16> %arg1) {
+; GFX7-LABEL: @uadd_sat_v2i16(
+; GFX7-NEXT: bb:
+; GFX7-NEXT: [[ARG0_0:%.*]] = extractelement <2 x i16> [[ARG0:%.*]], i64 0
+; GFX7-NEXT: [[ARG0_1:%.*]] = extractelement <2 x i16> [[ARG0]], i64 1
+; GFX7-NEXT: [[ARG1_0:%.*]] = extractelement <2 x i16> [[ARG1:%.*]], i64 0
+; GFX7-NEXT: [[ARG1_1:%.*]] = extractelement <2 x i16> [[ARG1]], i64 1
+; GFX7-NEXT: [[ADD_0:%.*]] = call i16 @llvm.umin.i16(i16 [[ARG0_0]], i16 [[ARG1_0]])
+; GFX7-NEXT: [[ADD_1:%.*]] = call i16 @llvm.umin.i16(i16 [[ARG0_1]], i16 [[ARG1_1]])
+; GFX7-NEXT: [[INS_0:%.*]] = insertelement <2 x i16> poison, i16 [[ADD_0]], i64 0
+; GFX7-NEXT: [[INS_1:%.*]] = insertelement <2 x i16> [[INS_0]], i16 [[ADD_1]], i64 1
+; GFX7-NEXT: ret <2 x i16> [[INS_1]]
+;
+; GFX8-LABEL: @uadd_sat_v2i16(
+; GFX8-NEXT: bb:
+; GFX8-NEXT: [[TMP0:%.*]] = call <2 x i16> @llvm.umin.v2i16(<2 x i16> [[ARG0:%.*]], <2 x i16> [[ARG1:%.*]])
+; GFX8-NEXT: ret <2 x i16> [[TMP0]]
+;
+; GFX9-LABEL: @uadd_sat_v2i16(
+; GFX9-NEXT: bb:
+; GFX9-NEXT: [[TMP0:%.*]] = call <2 x i16> @llvm.umin.v2i16(<2 x i16> [[ARG0:%.*]], <2 x i16> [[ARG1:%.*]])
+; GFX9-NEXT: ret <2 x i16> [[TMP0]]
+;
+bb:
+ %arg0.0 = extractelement <2 x i16> %arg0, i64 0
+ %arg0.1 = extractelement <2 x i16> %arg0, i64 1
+ %arg1.0 = extractelement <2 x i16> %arg1, i64 0
+ %arg1.1 = extractelement <2 x i16> %arg1, i64 1
+ %add.0 = call i16 @llvm.umin.i16(i16 %arg0.0, i16 %arg1.0)
+ %add.1 = call i16 @llvm.umin.i16(i16 %arg0.1, i16 %arg1.1)
+ %ins.0 = insertelement <2 x i16> undef, i16 %add.0, i64 0
+ %ins.1 = insertelement <2 x i16> %ins.0, i16 %add.1, i64 1
+ ret <2 x i16> %ins.1
+}
+
+define <2 x i16> @usub_sat_v2i16(<2 x i16> %arg0, <2 x i16> %arg1) {
+; GFX7-LABEL: @usub_sat_v2i16(
+; GFX7-NEXT: bb:
+; GFX7-NEXT: [[ARG0_0:%.*]] = extractelement <2 x i16> [[ARG0:%.*]], i64 0
+; GFX7-NEXT: [[ARG0_1:%.*]] = extractelement <2 x i16> [[ARG0]], i64 1
+; GFX7-NEXT: [[ARG1_0:%.*]] = extractelement <2 x i16> [[ARG1:%.*]], i64 0
+; GFX7-NEXT: [[ARG1_1:%.*]] = extractelement <2 x i16> [[ARG1]], i64 1
+; GFX7-NEXT: [[ADD_0:%.*]] = call i16 @llvm.umax.i16(i16 [[ARG0_0]], i16 [[ARG1_0]])
+; GFX7-NEXT: [[ADD_1:%.*]] = call i16 @llvm.umax.i16(i16 [[ARG0_1]], i16 [[ARG1_1]])
+; GFX7-NEXT: [[INS_0:%.*]] = insertelement <2 x i16> poison, i16 [[ADD_0]], i64 0
+; GFX7-NEXT: [[INS_1:%.*]] = insertelement <2 x i16> [[INS_0]], i16 [[ADD_1]], i64 1
+; GFX7-NEXT: ret <2 x i16> [[INS_1]]
+;
+; GFX8-LABEL: @usub_sat_v2i16(
+; GFX8-NEXT: bb:
+; GFX8-NEXT: [[TMP0:%.*]] = call <2 x i16> @llvm.umax.v2i16(<2 x i16> [[ARG0:%.*]], <2 x i16> [[ARG1:%.*]])
+; GFX8-NEXT: ret <2 x i16> [[TMP0]]
+;
+; GFX9-LABEL: @usub_sat_v2i16(
+; GFX9-NEXT: bb:
+; GFX9-NEXT: [[TMP0:%.*]] = call <2 x i16> @llvm.umax.v2i16(<2 x i16> [[ARG0:%.*]], <2 x i16> [[ARG1:%.*]])
+; GFX9-NEXT: ret <2 x i16> [[TMP0]]
+;
+bb:
+ %arg0.0 = extractelement <2 x i16> %arg0, i64 0
+ %arg0.1 = extractelement <2 x i16> %arg0, i64 1
+ %arg1.0 = extractelement <2 x i16> %arg1, i64 0
+ %arg1.1 = extractelement <2 x i16> %arg1, i64 1
+ %add.0 = call i16 @llvm.umax.i16(i16 %arg0.0, i16 %arg1.0)
+ %add.1 = call i16 @llvm.umax.i16(i16 %arg0.1, i16 %arg1.1)
+ %ins.0 = insertelement <2 x i16> undef, i16 %add.0, i64 0
+ %ins.1 = insertelement <2 x i16> %ins.0, i16 %add.1, i64 1
+ ret <2 x i16> %ins.1
+}
+
+define <2 x i16> @sadd_sat_v2i16(<2 x i16> %arg0, <2 x i16> %arg1) {
+; GFX7-LABEL: @sadd_sat_v2i16(
+; GFX7-NEXT: bb:
+; GFX7-NEXT: [[ARG0_0:%.*]] = extractelement <2 x i16> [[ARG0:%.*]], i64 0
+; GFX7-NEXT: [[ARG0_1:%.*]] = extractelement <2 x i16> [[ARG0]], i64 1
+; GFX7-NEXT: [[ARG1_0:%.*]] = extractelement <2 x i16> [[ARG1:%.*]], i64 0
+; GFX7-NEXT: [[ARG1_1:%.*]] = extractelement <2 x i16> [[ARG1]], i64 1
+; GFX7-NEXT: [[ADD_0:%.*]] = call i16 @llvm.smin.i16(i16 [[ARG0_0]], i16 [[ARG1_0]])
+; GFX7-NEXT: [[ADD_1:%.*]] = call i16 @llvm.smin.i16(i16 [[ARG0_1]], i16 [[ARG1_1]])
+; GFX7-NEXT: [[INS_0:%.*]] = insertelement <2 x i16> poison, i16 [[ADD_0]], i64 0
+; GFX7-NEXT: [[INS_1:%.*]] = insertelement <2 x i16> [[INS_0]], i16 [[ADD_1]], i64 1
+; GFX7-NEXT: ret <2 x i16> [[INS_1]]
+;
+; GFX8-LABEL: @sadd_sat_v2i16(
+; GFX8-NEXT: bb:
+; GFX8-NEXT: [[TMP0:%.*]] = call <2 x i16> @llvm.smin.v2i16(<2 x i16> [[ARG0:%.*]], <2 x i16> [[ARG1:%.*]])
+; GFX8-NEXT: ret <2 x i16> [[TMP0]]
+;
+; GFX9-LABEL: @sadd_sat_v2i16(
+; GFX9-NEXT: bb:
+; GFX9-NEXT: [[TMP0:%.*]] = call <2 x i16> @llvm.smin.v2i16(<2 x i16> [[ARG0:%.*]], <2 x i16> [[ARG1:%.*]])
+; GFX9-NEXT: ret <2 x i16> [[TMP0]]
+;
+bb:
+ %arg0.0 = extractelement <2 x i16> %arg0, i64 0
+ %arg0.1 = extractelement <2 x i16> %arg0, i64 1
+ %arg1.0 = extractelement <2 x i16> %arg1, i64 0
+ %arg1.1 = extractelement <2 x i16> %arg1, i64 1
+ %add.0 = call i16 @llvm.smin.i16(i16 %arg0.0, i16 %arg1.0)
+ %add.1 = call i16 @llvm.smin.i16(i16 %arg0.1, i16 %arg1.1)
+ %ins.0 = insertelement <2 x i16> undef, i16 %add.0, i64 0
+ %ins.1 = insertelement <2 x i16> %ins.0, i16 %add.1, i64 1
+ ret <2 x i16> %ins.1
+}
+
+define <2 x i16> @ssub_sat_v2i16(<2 x i16> %arg0, <2 x i16> %arg1) {
+; GFX7-LABEL: @ssub_sat_v2i16(
+; GFX7-NEXT: bb:
+; GFX7-NEXT: [[ARG0_0:%.*]] = extractelement <2 x i16> [[ARG0:%.*]], i64 0
+; GFX7-NEXT: [[ARG0_1:%.*]] = extractelement <2 x i16> [[ARG0]], i64 1
+; GFX7-NEXT: [[ARG1_0:%.*]] = extractelement <2 x i16> [[ARG1:%.*]], i64 0
+; GFX7-NEXT: [[ARG1_1:%.*]] = extractelement <2 x i16> [[ARG1]], i64 1
+; GFX7-NEXT: [[ADD_0:%.*]] = call i16 @llvm.smax.i16(i16 [[ARG0_0]], i16 [[ARG1_0]])
+; GFX7-NEXT: [[ADD_1:%.*]] = call i16 @llvm.smax.i16(i16 [[ARG0_1]], i16 [[ARG1_1]])
+; GFX7-NEXT: [[INS_0:%.*]] = insertelement <2 x i16> poison, i16 [[ADD_0]], i64 0
+; GFX7-NEXT: [[INS_1:%.*]] = insertelement <2 x i16> [[INS_0]], i16 [[ADD_1]], i64 1
+; GFX7-NEXT: ret <2 x i16> [[INS_1]]
+;
+; GFX8-LABEL: @ssub_sat_v2i16(
+; GFX8-NEXT: bb:
+; GFX8-NEXT: [[TMP0:%.*]] = call <2 x i16> @llvm.smax.v2i16(<2 x i16> [[ARG0:%.*]], <2 x i16> [[ARG1:%.*]])
+; GFX8-NEXT: ret <2 x i16> [[TMP0]]
+;
+; GFX9-LABEL: @ssub_sat_v2i16(
+; GFX9-NEXT: bb:
+; GFX9-NEXT: [[TMP0:%.*]] = call <2 x i16> @llvm.smax.v2i16(<2 x i16> [[ARG0:%.*]], <2 x i16> [[ARG1:%.*]])
+; GFX9-NEXT: ret <2 x i16> [[TMP0]]
+;
+bb:
+ %arg0.0 = extractelement <2 x i16> %arg0, i64 0
+ %arg0.1 = extractelement <2 x i16> %arg0, i64 1
+ %arg1.0 = extractelement <2 x i16> %arg1, i64 0
+ %arg1.1 = extractelement <2 x i16> %arg1, i64 1
+ %add.0 = call i16 @llvm.smax.i16(i16 %arg0.0, i16 %arg1.0)
+ %add.1 = call i16 @llvm.smax.i16(i16 %arg0.1, i16 %arg1.1)
+ %ins.0 = insertelement <2 x i16> undef, i16 %add.0, i64 0
+ %ins.1 = insertelement <2 x i16> %ins.0, i16 %add.1, i64 1
+ ret <2 x i16> %ins.1
+}
+
+define <2 x i32> @uadd_sat_v2i32(<2 x i32> %arg0, <2 x i32> %arg1) {
+; GCN-LABEL: @uadd_sat_v2i32(
+; GCN-NEXT: bb:
+; GCN-NEXT: [[ARG0_0:%.*]] = extractelement <2 x i32> [[ARG0:%.*]], i64 0
+; GCN-NEXT: [[ARG0_1:%.*]] = extractelement <2 x i32> [[ARG0]], i64 1
+; GCN-NEXT: [[ARG1_0:%.*]] = extractelement <2 x i32> [[ARG1:%.*]], i64 0
+; GCN-NEXT: [[ARG1_1:%.*]] = extractelement <2 x i32> [[ARG1]], i64 1
+; GCN-NEXT: [[ADD_0:%.*]] = call i32 @llvm.umin.i32(i32 [[ARG0_0]], i32 [[ARG1_0]])
+; GCN-NEXT: [[ADD_1:%.*]] = call i32 @llvm.umin.i32(i32 [[ARG0_1]], i32 [[ARG1_1]])
+; GCN-NEXT: [[INS_0:%.*]] = insertelement <2 x i32> poison, i32 [[ADD_0]], i64 0
+; GCN-NEXT: [[INS_1:%.*]] = insertelement <2 x i32> [[INS_0]], i32 [[ADD_1]], i64 1
+; GCN-NEXT: ret <2 x i32> [[INS_1]]
+;
+bb:
+ %arg0.0 = extractelement <2 x i32> %arg0, i64 0
+ %arg0.1 = extractelement <2 x i32> %arg0, i64 1
+ %arg1.0 = extractelement <2 x i32> %arg1, i64 0
+ %arg1.1 = extractelement <2 x i32> %arg1, i64 1
+ %add.0 = call i32 @llvm.umin.i32(i32 %arg0.0, i32 %arg1.0)
+ %add.1 = call i32 @llvm.umin.i32(i32 %arg0.1, i32 %arg1.1)
+ %ins.0 = insertelement <2 x i32> undef, i32 %add.0, i64 0
+ %ins.1 = insertelement <2 x i32> %ins.0, i32 %add.1, i64 1
+ ret <2 x i32> %ins.1
+}
+
+define <2 x i32> @usub_sat_v2i32(<2 x i32> %arg0, <2 x i32> %arg1) {
+; GCN-LABEL: @usub_sat_v2i32(
+; GCN-NEXT: bb:
+; GCN-NEXT: [[ARG0_0:%.*]] = extractelement <2 x i32> [[ARG0:%.*]], i64 0
+; GCN-NEXT: [[ARG0_1:%.*]] = extractelement <2 x i32> [[ARG0]], i64 1
+; GCN-NEXT: [[ARG1_0:%.*]] = extractelement <2 x i32> [[ARG1:%.*]], i64 0
+; GCN-NEXT: [[ARG1_1:%.*]] = extractelement <2 x i32> [[ARG1]], i64 1
+; GCN-NEXT: [[ADD_0:%.*]] = call i32 @llvm.umax.i32(i32 [[ARG0_0]], i32 [[ARG1_0]])
+; GCN-NEXT: [[ADD_1:%.*]] = call i32 @llvm.umax.i32(i32 [[ARG0_1]], i32 [[ARG1_1]])
+; GCN-NEXT: [[INS_0:%.*]] = insertelement <2 x i32> poison, i32 [[ADD_0]], i64 0
+; GCN-NEXT: [[INS_1:%.*]] = insertelement <2 x i32> [[INS_0]], i32 [[ADD_1]], i64 1
+; GCN-NEXT: ret <2 x i32> [[INS_1]]
+;
+bb:
+ %arg0.0 = extractelement <2 x i32> %arg0, i64 0
+ %arg0.1 = extractelement <2 x i32> %arg0, i64 1
+ %arg1.0 = extractelement <2 x i32> %arg1, i64 0
+ %arg1.1 = extractelement <2 x i32> %arg1, i64 1
+ %add.0 = call i32 @llvm.umax.i32(i32 %arg0.0, i32 %arg1.0)
+ %add.1 = call i32 @llvm.umax.i32(i32 %arg0.1, i32 %arg1.1)
+ %ins.0 = insertelement <2 x i32> undef, i32 %add.0, i64 0
+ %ins.1 = insertelement <2 x i32> %ins.0, i32 %add.1, i64 1
+ ret <2 x i32> %ins.1
+}
+
+define <2 x i32> @sadd_sat_v2i32(<2 x i32> %arg0, <2 x i32> %arg1) {
+; GCN-LABEL: @sadd_sat_v2i32(
+; GCN-NEXT: bb:
+; GCN-NEXT: [[ARG0_0:%.*]] = extractelement <2 x i32> [[ARG0:%.*]], i64 0
+; GCN-NEXT: [[ARG0_1:%.*]] = extractelement <2 x i32> [[ARG0]], i64 1
+; GCN-NEXT: [[ARG1_0:%.*]] = extractelement <2 x i32> [[ARG1:%.*]], i64 0
+; GCN-NEXT: [[ARG1_1:%.*]] = extractelement <2 x i32> [[ARG1]], i64 1
+; GCN-NEXT: [[ADD_0:%.*]] = call i32 @llvm.smin.i32(i32 [[ARG0_0]], i32 [[ARG1_0]])
+; GCN-NEXT: [[ADD_1:%.*]] = call i32 @llvm.smin.i32(i32 [[ARG0_1]], i32 [[ARG1_1]])
+; GCN-NEXT: [[INS_0:%.*]] = insertelement <2 x i32> poison, i32 [[ADD_0]], i64 0
+; GCN-NEXT: [[INS_1:%.*]] = insertelement <2 x i32> [[INS_0]], i32 [[ADD_1]], i64 1
+; GCN-NEXT: ret <2 x i32> [[INS_1]]
+;
+bb:
+ %arg0.0 = extractelement <2 x i32> %arg0, i64 0
+ %arg0.1 = extractelement <2 x i32> %arg0, i64 1
+ %arg1.0 = extractelement <2 x i32> %arg1, i64 0
+ %arg1.1 = extractelement <2 x i32> %arg1, i64 1
+ %add.0 = call i32 @llvm.smin.i32(i32 %arg0.0, i32 %arg1.0)
+ %add.1 = call i32 @llvm.smin.i32(i32 %arg0.1, i32 %arg1.1)
+ %ins.0 = insertelement <2 x i32> undef, i32 %add.0, i64 0
+ %ins.1 = insertelement <2 x i32> %ins.0, i32 %add.1, i64 1
+ ret <2 x i32> %ins.1
+}
+
+define <2 x i32> @ssub_sat_v2i32(<2 x i32> %arg0, <2 x i32> %arg1) {
+; GCN-LABEL: @ssub_sat_v2i32(
+; GCN-NEXT: bb:
+; GCN-NEXT: [[ARG0_0:%.*]] = extractelement <2 x i32> [[ARG0:%.*]], i64 0
+; GCN-NEXT: [[ARG0_1:%.*]] = extractelement <2 x i32> [[ARG0]], i64 1
+; GCN-NEXT: [[ARG1_0:%.*]] = extractelement <2 x i32> [[ARG1:%.*]], i64 0
+; GCN-NEXT: [[ARG1_1:%.*]] = extractelement <2 x i32> [[ARG1]], i64 1
+; GCN-NEXT: [[ADD_0:%.*]] = call i32 @llvm.smax.i32(i32 [[ARG0_0]], i32 [[ARG1_0]])
+; GCN-NEXT: [[ADD_1:%.*]] = call i32 @llvm.smax.i32(i32 [[ARG0_1]], i32 [[ARG1_1]])
+; GCN-NEXT: [[INS_0:%.*]] = insertelement <2 x i32> poison, i32 [[ADD_0]], i64 0
+; GCN-NEXT: [[INS_1:%.*]] = insertelement <2 x i32> [[INS_0]], i32 [[ADD_1]], i64 1
+; GCN-NEXT: ret <2 x i32> [[INS_1]]
+;
+bb:
+ %arg0.0 = extractelement <2 x i32> %arg0, i64 0
+ %arg0.1 = extractelement <2 x i32> %arg0, i64 1
+ %arg1.0 = extractelement <2 x i32> %arg1, i64 0
+ %arg1.1 = extractelement <2 x i32> %arg1, i64 1
+ %add.0 = call i32 @llvm.smax.i32(i32 %arg0.0, i32 %arg1.0)
+ %add.1 = call i32 @llvm.smax.i32(i32 %arg0.1, i32 %arg1.1)
+ %ins.0 = insertelement <2 x i32> undef, i32 %add.0, i64 0
+ %ins.1 = insertelement <2 x i32> %ins.0, i32 %add.1, i64 1
+ ret <2 x i32> %ins.1
+}
+
+define <3 x i16> @uadd_sat_v3i16(<3 x i16> %arg0, <3 x i16> %arg1) {
+; GFX7-LABEL: @uadd_sat_v3i16(
+; GFX7-NEXT: bb:
+; GFX7-NEXT: [[ARG0_0:%.*]] = extractelement <3 x i16> [[ARG0:%.*]], i64 0
+; GFX7-NEXT: [[ARG0_1:%.*]] = extractelement <3 x i16> [[ARG0]], i64 1
+; GFX7-NEXT: [[ARG0_2:%.*]] = extractelement <3 x i16> [[ARG0]], i64 2
+; GFX7-NEXT: [[ARG1_0:%.*]] = extractelement <3 x i16> [[ARG1:%.*]], i64 0
+; GFX7-NEXT: [[ARG1_1:%.*]] = extractelement <3 x i16> [[ARG1]], i64 1
+; GFX7-NEXT: [[ARG1_2:%.*]] = extractelement <3 x i16> [[ARG1]], i64 2
+; GFX7-NEXT: [[ADD_0:%.*]] = call i16 @llvm.umin.i16(i16 [[ARG0_0]], i16 [[ARG1_0]])
+; GFX7-NEXT: [[ADD_1:%.*]] = call i16 @llvm.umin.i16(i16 [[ARG0_1]], i16 [[ARG1_1]])
+; GFX7-NEXT: [[ADD_2:%.*]] = call i16 @llvm.umin.i16(i16 [[ARG0_2]], i16 [[ARG1_2]])
+; GFX7-NEXT: [[INS_0:%.*]] = insertelement <3 x i16> poison, i16 [[ADD_0]], i64 0
+; GFX7-NEXT: [[INS_1:%.*]] = insertelement <3 x i16> [[INS_0]], i16 [[ADD_1]], i64 1
+; GFX7-NEXT: [[INS_2:%.*]] = insertelement <3 x i16> [[INS_1]], i16 [[ADD_2]], i64 2
+; GFX7-NEXT: ret <3 x i16> [[INS_2]]
+;
+; GFX8-LABEL: @uadd_sat_v3i16(
+; GFX8-NEXT: bb:
+; GFX8-NEXT: [[ARG0_2:%.*]] = extractelement <3 x i16> [[ARG0:%.*]], i64 2
+; GFX8-NEXT: [[ARG1_2:%.*]] = extractelement <3 x i16> [[ARG1:%.*]], i64 2
+; GFX8-NEXT: [[TMP0:%.*]] = call <3 x i16> @llvm.umin.v3i16(<3 x i16> [[ARG0]], <3 x i16> [[ARG1]])
+; GFX8-NEXT: [[ADD_2:%.*]] = call i16 @llvm.umin.i16(i16 [[ARG0_2]], i16 [[ARG1_2]])
+; GFX8-NEXT: [[INS_2:%.*]] = insertelement <3 x i16> [[TMP0]], i16 [[ADD_2]], i64 2
+; GFX8-NEXT: ret <3 x i16> [[INS_2]]
+;
+; GFX9-LABEL: @uadd_sat_v3i16(
+; GFX9-NEXT: bb:
+; GFX9-NEXT: [[ARG0_2:%.*]] = extractelement <3 x i16> [[ARG0:%.*]], i64 2
+; GFX9-NEXT: [[ARG1_2:%.*]] = extractelement <3 x i16> [[ARG1:%.*]], i64 2
+; GFX9-NEXT: [[TMP0:%.*]] = call <3 x i16> @llvm.umin.v3i16(<3 x i16> [[ARG0]], <3 x i16> [[ARG1]])
+; GFX9-NEXT: [[ADD_2:%.*]] = call i16 @llvm.umin.i16(i16 [[ARG0_2]], i16 [[ARG1_2]])
+; GFX9-NEXT: [[INS_2:%.*]] = insertelement <3 x i16> [[TMP0]], i16 [[ADD_2]], i64 2
+; GFX9-NEXT: ret <3 x i16> [[INS_2]]
+;
+bb:
+ %arg0.0 = extractelement <3 x i16> %arg0, i64 0
+ %arg0.1 = extractelement <3 x i16> %arg0, i64 1
+ %arg0.2 = extractelement <3 x i16> %arg0, i64 2
+ %arg1.0 = extractelement <3 x i16> %arg1, i64 0
+ %arg1.1 = extractelement <3 x i16> %arg1, i64 1
+ %arg1.2 = extractelement <3 x i16> %arg1, i64 2
+ %add.0 = call i16 @llvm.umin.i16(i16 %arg0.0, i16 %arg1.0)
+ %add.1 = call i16 @llvm.umin.i16(i16 %arg0.1, i16 %arg1.1)
+ %add.2 = call i16 @llvm.umin.i16(i16 %arg0.2, i16 %arg1.2)
+ %ins.0 = insertelement <3 x i16> undef, i16 %add.0, i64 0
+ %ins.1 = insertelement <3 x i16> %ins.0, i16 %add.1, i64 1
+ %ins.2 = insertelement <3 x i16> %ins.1, i16 %add.2, i64 2
+ ret <3 x i16> %ins.2
+}
+
+define <4 x i16> @uadd_sat_v4i16(<4 x i16> %arg0, <4 x i16> %arg1) {
+; GFX7-LABEL: @uadd_sat_v4i16(
+; GFX7-NEXT: bb:
+; GFX7-NEXT: [[ARG0_0:%.*]] = extractelement <4 x i16> [[ARG0:%.*]], i64 0
+; GFX7-NEXT: [[ARG0_1:%.*]] = extractelement <4 x i16> [[ARG0]], i64 1
+; GFX7-NEXT: [[ARG0_2:%.*]] = extractelement <4 x i16> [[ARG0]], i64 2
+; GFX7-NEXT: [[ARG0_3:%.*]] = extractelement <4 x i16> [[ARG0]], i64 3
+; GFX7-NEXT: [[ARG1_0:%.*]] = extractelement <4 x i16> [[ARG1:%.*]], i64 0
+; GFX7-NEXT: [[ARG1_1:%.*]] = extractelement <4 x i16> [[ARG1]], i64 1
+; GFX7-NEXT: [[ARG1_2:%.*]] = extractelement <4 x i16> [[ARG1]], i64 2
+; GFX7-NEXT: [[ARG1_3:%.*]] = extractelement <4 x i16> [[ARG1]], i64 3
+; GFX7-NEXT: [[ADD_0:%.*]] = call i16 @llvm.umin.i16(i16 [[ARG0_0]], i16 [[ARG1_0]])
+; GFX7-NEXT: [[ADD_1:%.*]] = call i16 @llvm.umin.i16(i16 [[ARG0_1]], i16 [[ARG1_1]])
+; GFX7-NEXT: [[ADD_2:%.*]] = call i16 @llvm.umin.i16(i16 [[ARG0_2]], i16 [[ARG1_2]])
+; GFX7-NEXT: [[ADD_3:%.*]] = call i16 @llvm.umin.i16(i16 [[ARG0_3]], i16 [[ARG1_3]])
+; GFX7-NEXT: [[INS_0:%.*]] = insertelement <4 x i16> poison, i16 [[ADD_0]], i64 0
+; GFX7-NEXT: [[INS_1:%.*]] = insertelement <4 x i16> [[INS_0]], i16 [[ADD_1]], i64 1
+; GFX7-NEXT: [[INS_2:%.*]] = insertelement <4 x i16> [[INS_1]], i16 [[ADD_2]], i64 2
+; GFX7-NEXT: [[INS_3:%.*]] = insertelement <4 x i16> [[INS_2]], i16 [[ADD_3]], i64 3
+; GFX7-NEXT: ret <4 x i16> [[INS_3]]
+;
+; GFX8-LABEL: @uadd_sat_v4i16(
+; GFX8-NEXT: bb:
+; GFX8-NEXT: [[TMP0:%.*]] = call <4 x i16> @llvm.umin.v4i16(<4 x i16> [[ARG0:%.*]], <4 x i16> [[ARG1:%.*]])
+; GFX8-NEXT: [[TMP1:%.*]] = call <4 x i16> @llvm.umin.v4i16(<4 x i16> [[ARG0]], <4 x i16> [[ARG1]])
+; GFX8-NEXT: [[TMP2:%.*]] = shufflevector <4 x i16> [[TMP1]], <4 x i16> poison, <2 x i32> <i32 2, i32 3>
+; GFX8-NEXT: [[TMP3:%.*]] = shufflevector <2 x i16> [[TMP2]], <2 x i16> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
+; GFX8-NEXT: [[INS_31:%.*]] = shufflevector <4 x i16> [[TMP0]], <4 x i16> [[TMP3]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
+; GFX8-NEXT: ret <4 x i16> [[INS_31]]
+;
+; GFX9-LABEL: @uadd_sat_v4i16(
+; GFX9-NEXT: bb:
+; GFX9-NEXT: [[TMP0:%.*]] = call <4 x i16> @llvm.umin.v4i16(<4 x i16> [[ARG0:%.*]], <4 x i16> [[ARG1:%.*]])
+; GFX9-NEXT: [[TMP1:%.*]] = call <4 x i16> @llvm.umin.v4i16(<4 x i16> [[ARG0]], <4 x i16> [[ARG1]])
+; GFX9-NEXT: [[TMP2:%.*]] = shufflevector <4 x i16> [[TMP1]], <4 x i16> poison, <2 x i32> <i32 2, i32 3>
+; GFX9-NEXT: [[TMP3:%.*]] = shufflevector <2 x i16> [[TMP2]], <2 x i16> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
+; GFX9-NEXT: [[INS_31:%.*]] = shufflevector <4 x i16> [[TMP0]], <4 x i16> [[TMP3]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
+; GFX9-NEXT: ret <4 x i16> [[INS_31]]
+;
+bb:
+ %arg0.0 = extractelement <4 x i16> %arg0, i64 0
+ %arg0.1 = extractelement <4 x i16> %arg0, i64 1
+ %arg0.2 = extractelement <4 x i16> %arg0, i64 2
+ %arg0.3 = extractelement <4 x i16> %arg0, i64 3
+ %arg1.0 = extractelement <4 x i16> %arg1, i64 0
+ %arg1.1 = extractelement <4 x i16> %arg1, i64 1
+ %arg1.2 = extractelement <4 x i16> %arg1, i64 2
+ %arg1.3 = extractelement <4 x i16> %arg1, i64 3
+ %add.0 = call i16 @llvm.umin.i16(i16 %arg0.0, i16 %arg1.0)
+ %add.1 = call i16 @llvm.umin.i16(i16 %arg0.1, i16 %arg1.1)
+ %add.2 = call i16 @llvm.umin.i16(i16 %arg0.2, i16 %arg1.2)
+ %add.3 = call i16 @llvm.umin.i16(i16 %arg0.3, i16 %arg1.3)
+ %ins.0 = insertelement <4 x i16> undef, i16 %add.0, i64 0
+ %ins.1 = insertelement <4 x i16> %ins.0, i16 %add.1, i64 1
+ %ins.2 = insertelement <4 x i16> %ins.1, i16 %add.2, i64 2
+ %ins.3 = insertelement <4 x i16> %ins.2, i16 %add.3, i64 3
+ ret <4 x i16> %ins.3
+}
>From df2b6b7c749629f0ea50f7772329b48ba9450f2f Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault at amd.com>
Date: Thu, 25 Jul 2024 10:47:03 +0400
Subject: [PATCH 2/5] AMDGPU: Add baseline test for cost of abs intrinsics
---
llvm/test/Analysis/CostModel/AMDGPU/abs.ll | 310 +++++++++++++++++++++
1 file changed, 310 insertions(+)
create mode 100644 llvm/test/Analysis/CostModel/AMDGPU/abs.ll
diff --git a/llvm/test/Analysis/CostModel/AMDGPU/abs.ll b/llvm/test/Analysis/CostModel/AMDGPU/abs.ll
new file mode 100644
index 0000000000000..f65615b07abc0
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AMDGPU/abs.ll
@@ -0,0 +1,310 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=FAST %s
+; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=FAST %s
+; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=FAST %s
+; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=SLOW %s
+; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=FAST-SIZE %s
+; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=FAST-SIZE %s
+; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=FAST-SIZE %s
+; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=SLOW-SIZE %s
+; END.
+
+define void @abs_nonpoison() {
+; FAST-LABEL: 'abs_nonpoison'
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 114 for instruction: %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 174 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 198 for instruction: %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 322 for instruction: %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 false)
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; SLOW-LABEL: 'abs_nonpoison'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 102 for instruction: %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 162 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 198 for instruction: %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 322 for instruction: %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 false)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; FAST-SIZE-LABEL: 'abs_nonpoison'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 false)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+; SLOW-SIZE-LABEL: 'abs_nonpoison'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 false)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+ %I64 = call i64 @llvm.abs.i64(i64 undef, i1 false)
+ %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
+ %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
+ %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 false)
+ %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
+
+ %I32 = call i32 @llvm.abs.i32(i32 undef, i1 false)
+ %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 false)
+ %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 false)
+ %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 false)
+ %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 false)
+ %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 false)
+
+ %I16 = call i16 @llvm.abs.i16(i16 undef, i1 false)
+ %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 false)
+ %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 false)
+ %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 false)
+ %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 false)
+ %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 false)
+ %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 false)
+
+ %I8 = call i8 @llvm.abs.i8(i8 undef, i1 false)
+ %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false)
+ %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false)
+ %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false)
+ %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false)
+ %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 false)
+ %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 false)
+ %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 false)
+
+ ret void
+}
+
+define void @abs_poison() {
+; FAST-LABEL: 'abs_poison'
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 114 for instruction: %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 174 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 198 for instruction: %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 322 for instruction: %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 true)
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; SLOW-LABEL: 'abs_poison'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 102 for instruction: %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 162 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 198 for instruction: %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 322 for instruction: %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 true)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; FAST-SIZE-LABEL: 'abs_poison'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 true)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+; SLOW-SIZE-LABEL: 'abs_poison'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 true)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+ %I64 = call i64 @llvm.abs.i64(i64 undef, i1 true)
+ %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 true)
+ %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 true)
+ %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 true)
+ %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 true)
+
+ %I32 = call i32 @llvm.abs.i32(i32 undef, i1 true)
+ %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 true)
+ %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 true)
+ %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 true)
+ %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 true)
+ %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 true)
+
+ %I16 = call i16 @llvm.abs.i16(i16 undef, i1 true)
+ %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 true)
+ %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 true)
+ %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 true)
+ %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 true)
+ %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 true)
+ %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 true)
+
+ %I8 = call i8 @llvm.abs.i8(i8 undef, i1 true)
+ %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 true)
+ %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 true)
+ %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 true)
+ %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 true)
+ %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 true)
+ %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 true)
+ %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 true)
+
+ ret void
+}
>From 5d2e190921037f3d3fadbcea1eac80e7ad8e4cd3 Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault at amd.com>
Date: Mon, 13 Jul 2020 21:07:35 -0400
Subject: [PATCH 3/5] TTI: Fix special casing vectorization costs of saturating
add/sub
---
llvm/include/llvm/CodeGen/BasicTTIImpl.h | 48 +-
.../Analysis/CostModel/AArch64/arith-ssat.ll | 32 +-
.../Analysis/CostModel/AArch64/arith-usat.ll | 32 +-
.../CostModel/AArch64/sve-intrinsics.ll | 8 +-
.../CostModel/ARM/active_lane_mask.ll | 24 +-
.../test/Analysis/CostModel/ARM/arith-ssat.ll | 428 +++++++++---------
.../test/Analysis/CostModel/ARM/arith-usat.ll | 404 ++++++++---------
.../Analysis/CostModel/RISCV/int-sat-math.ll | 32 +-
.../LoopVectorize/AArch64/intrinsiccost.ll | 2 +-
.../LoopVectorize/ARM/mve-saddsatcost.ll | 4 +-
10 files changed, 493 insertions(+), 521 deletions(-)
diff --git a/llvm/include/llvm/CodeGen/BasicTTIImpl.h b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
index 5b9cc5dfeeadb..ee028be02ce6e 100644
--- a/llvm/include/llvm/CodeGen/BasicTTIImpl.h
+++ b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
@@ -2147,45 +2147,17 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
return Cost;
}
case Intrinsic::sadd_sat:
- case Intrinsic::ssub_sat: {
- Type *CondTy = RetTy->getWithNewBitWidth(1);
-
- Type *OpTy = StructType::create({RetTy, CondTy});
- Intrinsic::ID OverflowOp = IID == Intrinsic::sadd_sat
- ? Intrinsic::sadd_with_overflow
- : Intrinsic::ssub_with_overflow;
- CmpInst::Predicate Pred = CmpInst::ICMP_SGT;
-
- // SatMax -> Overflow && SumDiff < 0
- // SatMin -> Overflow && SumDiff >= 0
- InstructionCost Cost = 0;
- IntrinsicCostAttributes Attrs(OverflowOp, OpTy, {RetTy, RetTy}, FMF,
- nullptr, ScalarizationCostPassed);
- Cost += thisT()->getIntrinsicInstrCost(Attrs, CostKind);
- Cost += thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, RetTy, CondTy,
- Pred, CostKind);
- Cost += 2 * thisT()->getCmpSelInstrCost(BinaryOperator::Select, RetTy,
- CondTy, Pred, CostKind);
- return Cost;
- }
+ ISD = ISD::SADDSAT;
+ break;
+ case Intrinsic::ssub_sat:
+ ISD = ISD::SSUBSAT;
+ break;
case Intrinsic::uadd_sat:
- case Intrinsic::usub_sat: {
- Type *CondTy = RetTy->getWithNewBitWidth(1);
-
- Type *OpTy = StructType::create({RetTy, CondTy});
- Intrinsic::ID OverflowOp = IID == Intrinsic::uadd_sat
- ? Intrinsic::uadd_with_overflow
- : Intrinsic::usub_with_overflow;
-
- InstructionCost Cost = 0;
- IntrinsicCostAttributes Attrs(OverflowOp, OpTy, {RetTy, RetTy}, FMF,
- nullptr, ScalarizationCostPassed);
- Cost += thisT()->getIntrinsicInstrCost(Attrs, CostKind);
- Cost +=
- thisT()->getCmpSelInstrCost(BinaryOperator::Select, RetTy, CondTy,
- CmpInst::BAD_ICMP_PREDICATE, CostKind);
- return Cost;
- }
+ ISD = ISD::UADDSAT;
+ break;
+ case Intrinsic::usub_sat:
+ ISD = ISD::USUBSAT;
+ break;
case Intrinsic::smul_fix:
case Intrinsic::umul_fix: {
unsigned ExtSize = RetTy->getScalarSizeInBits() * 2;
diff --git a/llvm/test/Analysis/CostModel/AArch64/arith-ssat.ll b/llvm/test/Analysis/CostModel/AArch64/arith-ssat.ll
index 2267d9b88c970..d79eee53ecb48 100644
--- a/llvm/test/Analysis/CostModel/AArch64/arith-ssat.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/arith-ssat.ll
@@ -33,23 +33,23 @@ declare <64 x i8> @llvm.sadd.sat.v64i8(<64 x i8>, <64 x i8>)
define i32 @add(i32 %arg) {
; RECIP-LABEL: 'add'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V3I32 = call <3 x i32> @llvm.sadd.sat.v3i32(<3 x i32> undef, <3 x i32> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -59,23 +59,23 @@ define i32 @add(i32 %arg) {
; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SIZE-LABEL: 'add'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V3I32 = call <3 x i32> @llvm.sadd.sat.v3i32(<3 x i32> undef, <3 x i32> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -142,22 +142,22 @@ declare <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8>, <64 x i8>)
define i32 @sub(i32 %arg) {
; RECIP-LABEL: 'sub'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -167,22 +167,22 @@ define i32 @sub(i32 %arg) {
; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SIZE-LABEL: 'sub'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/AArch64/arith-usat.ll b/llvm/test/Analysis/CostModel/AArch64/arith-usat.ll
index 5a131f23847b1..c022a79ec2f38 100644
--- a/llvm/test/Analysis/CostModel/AArch64/arith-usat.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/arith-usat.ll
@@ -32,22 +32,22 @@ declare <64 x i8> @llvm.uadd.sat.v64i8(<64 x i8>, <64 x i8>)
define i32 @add(i32 %arg) {
; RECIP-LABEL: 'add'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -57,22 +57,22 @@ define i32 @add(i32 %arg) {
; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SIZE-LABEL: 'add'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -138,22 +138,22 @@ declare <64 x i8> @llvm.usub.sat.v64i8(<64 x i8>, <64 x i8>)
define i32 @sub(i32 %arg) {
; RECIP-LABEL: 'sub'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -163,22 +163,22 @@ define i32 @sub(i32 %arg) {
; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SIZE-LABEL: 'sub'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
index 1993023c91e26..004b696bb9a98 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
@@ -691,8 +691,8 @@ define void @get_lane_mask() #0 {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef)
@@ -701,8 +701,8 @@ define void @get_lane_mask() #0 {
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; TYPE_BASED_ONLY-LABEL: 'get_lane_mask'
diff --git a/llvm/test/Analysis/CostModel/ARM/active_lane_mask.ll b/llvm/test/Analysis/CostModel/ARM/active_lane_mask.ll
index cdd61c147fdad..204f05a767e93 100644
--- a/llvm/test/Analysis/CostModel/ARM/active_lane_mask.ll
+++ b/llvm/test/Analysis/CostModel/ARM/active_lane_mask.ll
@@ -3,18 +3,18 @@
define void @get_lane_mask() {
; CHECK-LABEL: 'get_lane_mask'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %mask_v8i1_i16 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i16(i16 undef, i16 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %mask_v4i1_i16 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i16(i16 undef, i16 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %mask_v2i1_i16 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 240 for instruction: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 120 for instruction: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 208 for instruction: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 208 for instruction: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %mask_v8i1_i16 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %mask_v4i1_i16 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %mask_v2i1_i16 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
%mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef)
diff --git a/llvm/test/Analysis/CostModel/ARM/arith-ssat.ll b/llvm/test/Analysis/CostModel/ARM/arith-ssat.ll
index ba1d163882bcb..804dc89b7808e 100644
--- a/llvm/test/Analysis/CostModel/ARM/arith-ssat.ll
+++ b/llvm/test/Analysis/CostModel/ARM/arith-ssat.ll
@@ -37,72 +37,72 @@ declare <64 x i8> @llvm.sadd.sat.v64i8(<64 x i8>, <64 x i8>)
define i32 @add(i32 %arg) {
; V8M-RECIP-LABEL: 'add'
; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 384 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 384 for instruction: %V32I8 = call <32 x i8> @llvm.sadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 768 for instruction: %V64I8 = call <64 x i8> @llvm.sadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32I8 = call <32 x i8> @llvm.sadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 704 for instruction: %V64I8 = call <64 x i8> @llvm.sadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; NEON-RECIP-LABEL: 'add'
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 117 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V32I8 = call <32 x i8> @llvm.sadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64I8 = call <64 x i8> @llvm.sadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.sadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.sadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; MVE-RECIP-LABEL: 'add'
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 166 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 298 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 594 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -111,73 +111,73 @@ define i32 @add(i32 %arg) {
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; V8M-SIZE-LABEL: 'add'
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V32I8 = call <32 x i8> @llvm.sadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V64I8 = call <64 x i8> @llvm.sadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I8 = call <32 x i8> @llvm.sadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64I8 = call <64 x i8> @llvm.sadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; NEON-SIZE-LABEL: 'add'
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 105 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V32I8 = call <32 x i8> @llvm.sadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64I8 = call <64 x i8> @llvm.sadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.sadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.sadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; MVE-SIZE-LABEL: 'add'
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 78 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 150 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -243,72 +243,72 @@ declare <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8>, <64 x i8>)
define i32 @sub(i32 %arg) {
; V8M-RECIP-LABEL: 'sub'
; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 384 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 384 for instruction: %V32I8 = call <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 768 for instruction: %V64I8 = call <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32I8 = call <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 704 for instruction: %V64I8 = call <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; NEON-RECIP-LABEL: 'sub'
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 117 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V32I8 = call <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64I8 = call <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; MVE-RECIP-LABEL: 'sub'
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 166 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 298 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 594 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -317,73 +317,73 @@ define i32 @sub(i32 %arg) {
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; V8M-SIZE-LABEL: 'sub'
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V32I8 = call <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V64I8 = call <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I8 = call <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64I8 = call <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; NEON-SIZE-LABEL: 'sub'
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 105 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V32I8 = call <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64I8 = call <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; MVE-SIZE-LABEL: 'sub'
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 78 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 150 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/ARM/arith-usat.ll b/llvm/test/Analysis/CostModel/ARM/arith-usat.ll
index 3b755f9a55f4f..3575b74d27a1a 100644
--- a/llvm/test/Analysis/CostModel/ARM/arith-usat.ll
+++ b/llvm/test/Analysis/CostModel/ARM/arith-usat.ll
@@ -36,73 +36,73 @@ declare <64 x i8> @llvm.uadd.sat.v64i8(<64 x i8>, <64 x i8>)
define i32 @add(i32 %arg) {
; V8M-RECIP-LABEL: 'add'
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32I8 = call <32 x i8> @llvm.uadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V64I8 = call <64 x i8> @llvm.uadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32I8 = call <32 x i8> @llvm.uadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 704 for instruction: %V64I8 = call <64 x i8> @llvm.uadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; NEON-RECIP-LABEL: 'add'
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V32I8 = call <32 x i8> @llvm.uadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64I8 = call <64 x i8> @llvm.uadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.uadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.uadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; MVE-RECIP-LABEL: 'add'
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 148 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 296 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -111,73 +111,73 @@ define i32 @add(i32 %arg) {
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; V8M-SIZE-LABEL: 'add'
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call <32 x i8> @llvm.uadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V64I8 = call <64 x i8> @llvm.uadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I8 = call <32 x i8> @llvm.uadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64I8 = call <64 x i8> @llvm.uadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; NEON-SIZE-LABEL: 'add'
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.uadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V64I8 = call <64 x i8> @llvm.uadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.uadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; MVE-SIZE-LABEL: 'add'
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 146 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -242,73 +242,73 @@ declare <64 x i8> @llvm.usub.sat.v64i8(<64 x i8>, <64 x i8>)
define i32 @sub(i32 %arg) {
; V8M-RECIP-LABEL: 'sub'
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32I8 = call <32 x i8> @llvm.usub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V64I8 = call <64 x i8> @llvm.usub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32I8 = call <32 x i8> @llvm.usub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 704 for instruction: %V64I8 = call <64 x i8> @llvm.usub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; NEON-RECIP-LABEL: 'sub'
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V32I8 = call <32 x i8> @llvm.usub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64I8 = call <64 x i8> @llvm.usub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.usub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.usub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; MVE-RECIP-LABEL: 'sub'
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 148 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 296 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -317,73 +317,73 @@ define i32 @sub(i32 %arg) {
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; V8M-SIZE-LABEL: 'sub'
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call <32 x i8> @llvm.usub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V64I8 = call <64 x i8> @llvm.usub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I8 = call <32 x i8> @llvm.usub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64I8 = call <64 x i8> @llvm.usub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; NEON-SIZE-LABEL: 'sub'
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.usub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V64I8 = call <64 x i8> @llvm.usub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.usub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; MVE-SIZE-LABEL: 'sub'
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 146 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll b/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll
index 541534d2778aa..cdf33a11e2f14 100644
--- a/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll
@@ -3,7 +3,7 @@
define void @sadd.sat() {
; CHECK-LABEL: 'sadd.sat'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %1 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %1 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -12,7 +12,7 @@ define void @sadd.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.sadd.sat.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.sadd.sat.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.sadd.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %10 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
@@ -21,7 +21,7 @@ define void @sadd.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.sadd.sat.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.sadd.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.sadd.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %19 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %19 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
@@ -30,7 +30,7 @@ define void @sadd.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.sadd.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.sadd.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.sadd.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %28 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %28 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
@@ -80,7 +80,7 @@ define void @sadd.sat() {
define void @uadd.sat() {
; CHECK-LABEL: 'uadd.sat'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %1 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %1 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -89,7 +89,7 @@ define void @uadd.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.uadd.sat.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.uadd.sat.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.uadd.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %10 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %10 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
@@ -98,7 +98,7 @@ define void @uadd.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.uadd.sat.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.uadd.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.uadd.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %19 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %19 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
@@ -107,7 +107,7 @@ define void @uadd.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.uadd.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.uadd.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.uadd.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %28 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %28 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
@@ -157,7 +157,7 @@ define void @uadd.sat() {
define void @usub.sat() {
; CHECK-LABEL: 'usub.sat'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %1 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %1 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -166,7 +166,7 @@ define void @usub.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.usub.sat.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.usub.sat.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.usub.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %10 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %10 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
@@ -175,7 +175,7 @@ define void @usub.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.usub.sat.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.usub.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.usub.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %19 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %19 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
@@ -184,7 +184,7 @@ define void @usub.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.usub.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.usub.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.usub.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %28 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %28 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
@@ -234,7 +234,7 @@ define void @usub.sat() {
define void @ssub.sat() {
; CHECK-LABEL: 'ssub.sat'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %1 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %1 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -243,7 +243,7 @@ define void @ssub.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.ssub.sat.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.ssub.sat.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.ssub.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %10 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
@@ -252,7 +252,7 @@ define void @ssub.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.ssub.sat.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.ssub.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.ssub.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %19 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %19 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
@@ -261,7 +261,7 @@ define void @ssub.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.ssub.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.ssub.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.ssub.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %28 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %28 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/intrinsiccost.ll b/llvm/test/Transforms/LoopVectorize/AArch64/intrinsiccost.ll
index 0f26092f510ca..a60f246c9e860 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/intrinsiccost.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/intrinsiccost.ll
@@ -7,7 +7,7 @@ target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
target triple = "aarch64--linux-gnu"
; CHECK-COST-LABEL: sadd
-; CHECK-COST: Found an estimated cost of 6 for VF 1 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
+; CHECK-COST: Found an estimated cost of 10 for VF 1 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
; CHECK-COST: Found an estimated cost of 4 for VF 2 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
; CHECK-COST: Found an estimated cost of 1 for VF 4 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
; CHECK-COST: Found an estimated cost of 1 for VF 8 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
diff --git a/llvm/test/Transforms/LoopVectorize/ARM/mve-saddsatcost.ll b/llvm/test/Transforms/LoopVectorize/ARM/mve-saddsatcost.ll
index 0515ccea94b5b..44d17d09307b3 100644
--- a/llvm/test/Transforms/LoopVectorize/ARM/mve-saddsatcost.ll
+++ b/llvm/test/Transforms/LoopVectorize/ARM/mve-saddsatcost.ll
@@ -7,8 +7,8 @@ target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "thumbv8.1m.main-arm-none-eabi"
; CHECK-COST-LABEL: arm_offset_q15
-; CHECK-COST: Found an estimated cost of 7 for VF 1 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
-; CHECK-COST: Found an estimated cost of 36 for VF 2 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
+; CHECK-COST: Found an estimated cost of 1 for VF 1 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
+; CHECK-COST: Found an estimated cost of 26 for VF 2 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
; CHECK-COST: Found an estimated cost of 8 for VF 4 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
; CHECK-COST: Found an estimated cost of 2 for VF 8 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
>From 6d657997108fb1cb0898e05fc4457645f7b90fa4 Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault at amd.com>
Date: Thu, 25 Jul 2024 00:30:59 +0400
Subject: [PATCH 4/5] compute approx default expansion cost in expand case
---
llvm/include/llvm/CodeGen/BasicTTIImpl.h | 41 +++
.../Analysis/CostModel/AArch64/arith-ssat.ll | 32 +--
.../Analysis/CostModel/AArch64/arith-usat.ll | 32 +--
.../CostModel/ARM/active_lane_mask.ll | 24 +-
.../test/Analysis/CostModel/ARM/arith-ssat.ll | 220 +++++++-------
.../test/Analysis/CostModel/ARM/arith-usat.ll | 272 +++++++++---------
.../Analysis/CostModel/RISCV/int-sat-math.ll | 32 +--
.../LoopVectorize/AArch64/intrinsiccost.ll | 88 +++---
.../LoopVectorize/ARM/mve-saddsatcost.ll | 22 +-
9 files changed, 402 insertions(+), 361 deletions(-)
diff --git a/llvm/include/llvm/CodeGen/BasicTTIImpl.h b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
index ee028be02ce6e..2d2efc877024e 100644
--- a/llvm/include/llvm/CodeGen/BasicTTIImpl.h
+++ b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
@@ -2339,6 +2339,47 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
thisT()->getIntrinsicInstrCost(FAddAttrs, CostKind);
}
+ if (IID == Intrinsic::sadd_sat || IID == Intrinsic::ssub_sat) {
+ // Assume a default expansion.
+ Type *CondTy = RetTy->getWithNewBitWidth(1);
+
+ Type *OpTy = StructType::create({RetTy, CondTy});
+ Intrinsic::ID OverflowOp = IID == Intrinsic::sadd_sat
+ ? Intrinsic::sadd_with_overflow
+ : Intrinsic::ssub_with_overflow;
+ CmpInst::Predicate Pred = CmpInst::ICMP_SGT;
+
+ // SatMax -> Overflow && SumDiff < 0
+ // SatMin -> Overflow && SumDiff >= 0
+ InstructionCost Cost = 0;
+ IntrinsicCostAttributes Attrs(OverflowOp, OpTy, {RetTy, RetTy}, FMF,
+ nullptr, ScalarizationCostPassed);
+ Cost += thisT()->getIntrinsicInstrCost(Attrs, CostKind);
+ Cost += thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, RetTy, CondTy,
+ Pred, CostKind);
+ Cost += 2 * thisT()->getCmpSelInstrCost(BinaryOperator::Select, RetTy,
+ CondTy, Pred, CostKind);
+ return Cost;
+ }
+
+ if (IID == Intrinsic::uadd_sat || IID == Intrinsic::usub_sat) {
+ Type *CondTy = RetTy->getWithNewBitWidth(1);
+
+ Type *OpTy = StructType::create({RetTy, CondTy});
+ Intrinsic::ID OverflowOp = IID == Intrinsic::uadd_sat
+ ? Intrinsic::uadd_with_overflow
+ : Intrinsic::usub_with_overflow;
+
+ InstructionCost Cost = 0;
+ IntrinsicCostAttributes Attrs(OverflowOp, OpTy, {RetTy, RetTy}, FMF,
+ nullptr, ScalarizationCostPassed);
+ Cost += thisT()->getIntrinsicInstrCost(Attrs, CostKind);
+ Cost +=
+ thisT()->getCmpSelInstrCost(BinaryOperator::Select, RetTy, CondTy,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
+ return Cost;
+ }
+
// Else, assume that we need to scalarize this intrinsic. For math builtins
// this will emit a costly libcall, adding call overhead and spills. Make it
// very expensive.
diff --git a/llvm/test/Analysis/CostModel/AArch64/arith-ssat.ll b/llvm/test/Analysis/CostModel/AArch64/arith-ssat.ll
index d79eee53ecb48..2267d9b88c970 100644
--- a/llvm/test/Analysis/CostModel/AArch64/arith-ssat.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/arith-ssat.ll
@@ -33,23 +33,23 @@ declare <64 x i8> @llvm.sadd.sat.v64i8(<64 x i8>, <64 x i8>)
define i32 @add(i32 %arg) {
; RECIP-LABEL: 'add'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V3I32 = call <3 x i32> @llvm.sadd.sat.v3i32(<3 x i32> undef, <3 x i32> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -59,23 +59,23 @@ define i32 @add(i32 %arg) {
; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SIZE-LABEL: 'add'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V3I32 = call <3 x i32> @llvm.sadd.sat.v3i32(<3 x i32> undef, <3 x i32> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -142,22 +142,22 @@ declare <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8>, <64 x i8>)
define i32 @sub(i32 %arg) {
; RECIP-LABEL: 'sub'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -167,22 +167,22 @@ define i32 @sub(i32 %arg) {
; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SIZE-LABEL: 'sub'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/AArch64/arith-usat.ll b/llvm/test/Analysis/CostModel/AArch64/arith-usat.ll
index c022a79ec2f38..5a131f23847b1 100644
--- a/llvm/test/Analysis/CostModel/AArch64/arith-usat.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/arith-usat.ll
@@ -32,22 +32,22 @@ declare <64 x i8> @llvm.uadd.sat.v64i8(<64 x i8>, <64 x i8>)
define i32 @add(i32 %arg) {
; RECIP-LABEL: 'add'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -57,22 +57,22 @@ define i32 @add(i32 %arg) {
; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SIZE-LABEL: 'add'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -138,22 +138,22 @@ declare <64 x i8> @llvm.usub.sat.v64i8(<64 x i8>, <64 x i8>)
define i32 @sub(i32 %arg) {
; RECIP-LABEL: 'sub'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -163,22 +163,22 @@ define i32 @sub(i32 %arg) {
; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SIZE-LABEL: 'sub'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/ARM/active_lane_mask.ll b/llvm/test/Analysis/CostModel/ARM/active_lane_mask.ll
index 204f05a767e93..cdd61c147fdad 100644
--- a/llvm/test/Analysis/CostModel/ARM/active_lane_mask.ll
+++ b/llvm/test/Analysis/CostModel/ARM/active_lane_mask.ll
@@ -3,18 +3,18 @@
define void @get_lane_mask() {
; CHECK-LABEL: 'get_lane_mask'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 240 for instruction: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 120 for instruction: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 208 for instruction: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 208 for instruction: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %mask_v8i1_i16 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i16(i16 undef, i16 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %mask_v4i1_i16 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i16(i16 undef, i16 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %mask_v2i1_i16 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %mask_v8i1_i16 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %mask_v4i1_i16 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %mask_v2i1_i16 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
%mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef)
diff --git a/llvm/test/Analysis/CostModel/ARM/arith-ssat.ll b/llvm/test/Analysis/CostModel/ARM/arith-ssat.ll
index 804dc89b7808e..7317118ec1b4d 100644
--- a/llvm/test/Analysis/CostModel/ARM/arith-ssat.ll
+++ b/llvm/test/Analysis/CostModel/ARM/arith-ssat.ll
@@ -37,27 +37,27 @@ declare <64 x i8> @llvm.sadd.sat.v64i8(<64 x i8>, <64 x i8>)
define i32 @add(i32 %arg) {
; V8M-RECIP-LABEL: 'add'
; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32I8 = call <32 x i8> @llvm.sadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 704 for instruction: %V64I8 = call <64 x i8> @llvm.sadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 384 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 384 for instruction: %V32I8 = call <32 x i8> @llvm.sadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 768 for instruction: %V64I8 = call <64 x i8> @llvm.sadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; NEON-RECIP-LABEL: 'add'
@@ -87,22 +87,22 @@ define i32 @add(i32 %arg) {
;
; MVE-RECIP-LABEL: 'add'
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 166 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 298 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 594 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -111,28 +111,28 @@ define i32 @add(i32 %arg) {
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; V8M-SIZE-LABEL: 'add'
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I8 = call <32 x i8> @llvm.sadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64I8 = call <64 x i8> @llvm.sadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V32I8 = call <32 x i8> @llvm.sadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V64I8 = call <64 x i8> @llvm.sadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; NEON-SIZE-LABEL: 'add'
@@ -162,22 +162,22 @@ define i32 @add(i32 %arg) {
;
; MVE-SIZE-LABEL: 'add'
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V2I64 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 78 for instruction: %V4I64 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 150 for instruction: %V8I64 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V2I32 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V2I16 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V2I8 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -243,27 +243,27 @@ declare <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8>, <64 x i8>)
define i32 @sub(i32 %arg) {
; V8M-RECIP-LABEL: 'sub'
; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32I8 = call <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 704 for instruction: %V64I8 = call <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 384 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 384 for instruction: %V32I8 = call <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 768 for instruction: %V64I8 = call <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; NEON-RECIP-LABEL: 'sub'
@@ -293,22 +293,22 @@ define i32 @sub(i32 %arg) {
;
; MVE-RECIP-LABEL: 'sub'
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 166 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 298 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 594 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -317,28 +317,28 @@ define i32 @sub(i32 %arg) {
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; V8M-SIZE-LABEL: 'sub'
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I8 = call <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64I8 = call <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V32I8 = call <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V64I8 = call <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; NEON-SIZE-LABEL: 'sub'
@@ -368,22 +368,22 @@ define i32 @sub(i32 %arg) {
;
; MVE-SIZE-LABEL: 'sub'
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V2I64 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 78 for instruction: %V4I64 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 150 for instruction: %V8I64 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V2I32 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V2I16 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V2I8 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/ARM/arith-usat.ll b/llvm/test/Analysis/CostModel/ARM/arith-usat.ll
index 3575b74d27a1a..9ad4b1974a419 100644
--- a/llvm/test/Analysis/CostModel/ARM/arith-usat.ll
+++ b/llvm/test/Analysis/CostModel/ARM/arith-usat.ll
@@ -36,47 +36,47 @@ declare <64 x i8> @llvm.uadd.sat.v64i8(<64 x i8>, <64 x i8>)
define i32 @add(i32 %arg) {
; V8M-RECIP-LABEL: 'add'
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32I8 = call <32 x i8> @llvm.uadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 704 for instruction: %V64I8 = call <64 x i8> @llvm.uadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32I8 = call <32 x i8> @llvm.uadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V64I8 = call <64 x i8> @llvm.uadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; NEON-RECIP-LABEL: 'add'
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -86,23 +86,23 @@ define i32 @add(i32 %arg) {
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; MVE-RECIP-LABEL: 'add'
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 148 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 296 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -111,47 +111,47 @@ define i32 @add(i32 %arg) {
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; V8M-SIZE-LABEL: 'add'
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I8 = call <32 x i8> @llvm.uadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64I8 = call <64 x i8> @llvm.uadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call <32 x i8> @llvm.uadd.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V64I8 = call <64 x i8> @llvm.uadd.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; NEON-SIZE-LABEL: 'add'
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -161,23 +161,23 @@ define i32 @add(i32 %arg) {
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; MVE-SIZE-LABEL: 'add'
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I64 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V2I64 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V4I64 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 146 for instruction: %V8I64 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2I32 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2I16 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2I8 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -242,47 +242,47 @@ declare <64 x i8> @llvm.usub.sat.v64i8(<64 x i8>, <64 x i8>)
define i32 @sub(i32 %arg) {
; V8M-RECIP-LABEL: 'sub'
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 352 for instruction: %V32I8 = call <32 x i8> @llvm.usub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 704 for instruction: %V64I8 = call <64 x i8> @llvm.usub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32I8 = call <32 x i8> @llvm.usub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V64I8 = call <64 x i8> @llvm.usub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; NEON-RECIP-LABEL: 'sub'
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -292,23 +292,23 @@ define i32 @sub(i32 %arg) {
; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; MVE-RECIP-LABEL: 'sub'
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 148 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 296 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
@@ -317,47 +317,47 @@ define i32 @sub(i32 %arg) {
; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; V8M-SIZE-LABEL: 'sub'
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I8 = call <32 x i8> @llvm.usub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
-; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64I8 = call <64 x i8> @llvm.usub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call <32 x i8> @llvm.usub.sat.v32i8(<32 x i8> undef, <32 x i8> undef)
+; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V64I8 = call <64 x i8> @llvm.usub.sat.v64i8(<64 x i8> undef, <64 x i8> undef)
; V8M-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; NEON-SIZE-LABEL: 'sub'
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -367,23 +367,23 @@ define i32 @sub(i32 %arg) {
; NEON-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; MVE-SIZE-LABEL: 'sub'
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I64 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V2I64 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V4I64 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 146 for instruction: %V8I64 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2I32 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2I16 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> undef, <32 x i16> undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
-; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V2I8 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll b/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll
index cdf33a11e2f14..541534d2778aa 100644
--- a/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll
@@ -3,7 +3,7 @@
define void @sadd.sat() {
; CHECK-LABEL: 'sadd.sat'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %1 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %1 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x i8> @llvm.sadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -12,7 +12,7 @@ define void @sadd.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.sadd.sat.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.sadd.sat.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.sadd.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %10 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
@@ -21,7 +21,7 @@ define void @sadd.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.sadd.sat.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.sadd.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.sadd.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %19 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %19 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
@@ -30,7 +30,7 @@ define void @sadd.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.sadd.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.sadd.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.sadd.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %28 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %28 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
@@ -80,7 +80,7 @@ define void @sadd.sat() {
define void @uadd.sat() {
; CHECK-LABEL: 'uadd.sat'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %1 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %1 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x i8> @llvm.uadd.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -89,7 +89,7 @@ define void @uadd.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.uadd.sat.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.uadd.sat.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.uadd.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %10 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %10 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
@@ -98,7 +98,7 @@ define void @uadd.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.uadd.sat.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.uadd.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.uadd.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %19 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %19 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
@@ -107,7 +107,7 @@ define void @uadd.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.uadd.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.uadd.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.uadd.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %28 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %28 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
@@ -157,7 +157,7 @@ define void @uadd.sat() {
define void @usub.sat() {
; CHECK-LABEL: 'usub.sat'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %1 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %1 = call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x i8> @llvm.usub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -166,7 +166,7 @@ define void @usub.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.usub.sat.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.usub.sat.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.usub.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %10 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %10 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
@@ -175,7 +175,7 @@ define void @usub.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.usub.sat.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.usub.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.usub.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %19 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %19 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
@@ -184,7 +184,7 @@ define void @usub.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.usub.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.usub.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.usub.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %28 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %28 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
@@ -234,7 +234,7 @@ define void @usub.sat() {
define void @ssub.sat() {
; CHECK-LABEL: 'ssub.sat'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %1 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %1 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> undef, <2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
@@ -243,7 +243,7 @@ define void @ssub.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.ssub.sat.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.ssub.sat.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.ssub.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %10 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
@@ -252,7 +252,7 @@ define void @ssub.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.ssub.sat.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.ssub.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.ssub.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %19 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %19 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
@@ -261,7 +261,7 @@ define void @ssub.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.ssub.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.ssub.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.ssub.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %28 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %28 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/intrinsiccost.ll b/llvm/test/Transforms/LoopVectorize/AArch64/intrinsiccost.ll
index a60f246c9e860..c9990487665b9 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/intrinsiccost.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/intrinsiccost.ll
@@ -7,7 +7,7 @@ target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
target triple = "aarch64--linux-gnu"
; CHECK-COST-LABEL: sadd
-; CHECK-COST: Found an estimated cost of 10 for VF 1 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
+; CHECK-COST: Found an estimated cost of 6 for VF 1 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
; CHECK-COST: Found an estimated cost of 4 for VF 2 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
; CHECK-COST: Found an estimated cost of 1 for VF 4 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
; CHECK-COST: Found an estimated cost of 1 for VF 8 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
@@ -34,21 +34,21 @@ define void @saddsat(ptr nocapture readonly %pSrc, i16 signext %offset, ptr noca
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[TMP3:%.*]] = shl i64 [[INDEX]], 1
-; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[PSRC]], i64 [[TMP3]]
-; CHECK-NEXT: [[TMP4:%.*]] = shl i64 [[INDEX]], 1
-; CHECK-NEXT: [[NEXT_GEP6:%.*]] = getelementptr i8, ptr [[PDST]], i64 [[TMP4]]
-; CHECK-NEXT: [[TMP5:%.*]] = getelementptr i8, ptr [[NEXT_GEP]], i64 16
+; CHECK-NEXT: [[OFFSET_IDX:%.*]] = shl i64 [[INDEX]], 1
+; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[PSRC]], i64 [[OFFSET_IDX]]
+; CHECK-NEXT: [[OFFSET_IDX6:%.*]] = shl i64 [[INDEX]], 1
+; CHECK-NEXT: [[NEXT_GEP7:%.*]] = getelementptr i8, ptr [[PDST]], i64 [[OFFSET_IDX6]]
+; CHECK-NEXT: [[TMP3:%.*]] = getelementptr i8, ptr [[NEXT_GEP]], i64 16
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <8 x i16>, ptr [[NEXT_GEP]], align 2
-; CHECK-NEXT: [[WIDE_LOAD8:%.*]] = load <8 x i16>, ptr [[TMP5]], align 2
-; CHECK-NEXT: [[TMP6:%.*]] = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> [[WIDE_LOAD]], <8 x i16> [[BROADCAST_SPLAT]])
-; CHECK-NEXT: [[TMP7:%.*]] = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> [[WIDE_LOAD8]], <8 x i16> [[BROADCAST_SPLAT]])
-; CHECK-NEXT: [[TMP8:%.*]] = getelementptr i8, ptr [[NEXT_GEP6]], i64 16
-; CHECK-NEXT: store <8 x i16> [[TMP6]], ptr [[NEXT_GEP6]], align 2
-; CHECK-NEXT: store <8 x i16> [[TMP7]], ptr [[TMP8]], align 2
+; CHECK-NEXT: [[WIDE_LOAD9:%.*]] = load <8 x i16>, ptr [[TMP3]], align 2
+; CHECK-NEXT: [[TMP4:%.*]] = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> [[WIDE_LOAD]], <8 x i16> [[BROADCAST_SPLAT]])
+; CHECK-NEXT: [[TMP5:%.*]] = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> [[WIDE_LOAD9]], <8 x i16> [[BROADCAST_SPLAT]])
+; CHECK-NEXT: [[TMP6:%.*]] = getelementptr i8, ptr [[NEXT_GEP7]], i64 16
+; CHECK-NEXT: store <8 x i16> [[TMP4]], ptr [[NEXT_GEP7]], align 2
+; CHECK-NEXT: store <8 x i16> [[TMP5]], ptr [[TMP6]], align 2
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
-; CHECK-NEXT: [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N_VEC]], [[TMP0]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[WHILE_END]], label [[SCALAR_PH]]
@@ -62,10 +62,10 @@ define void @saddsat(ptr nocapture readonly %pSrc, i16 signext %offset, ptr noca
; CHECK-NEXT: [[PSRC_ADDR_08:%.*]] = phi ptr [ [[INCDEC_PTR:%.*]], [[WHILE_BODY]] ], [ [[BC_RESUME_VAL2]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[PDST_ADDR_07:%.*]] = phi ptr [ [[INCDEC_PTR3:%.*]], [[WHILE_BODY]] ], [ [[BC_RESUME_VAL4]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds i8, ptr [[PSRC_ADDR_08]], i64 2
-; CHECK-NEXT: [[TMP10:%.*]] = load i16, ptr [[PSRC_ADDR_08]], align 2
-; CHECK-NEXT: [[TMP11:%.*]] = tail call i16 @llvm.sadd.sat.i16(i16 [[TMP10]], i16 [[OFFSET]])
+; CHECK-NEXT: [[TMP8:%.*]] = load i16, ptr [[PSRC_ADDR_08]], align 2
+; CHECK-NEXT: [[TMP9:%.*]] = tail call i16 @llvm.sadd.sat.i16(i16 [[TMP8]], i16 [[OFFSET]])
; CHECK-NEXT: [[INCDEC_PTR3]] = getelementptr inbounds i8, ptr [[PDST_ADDR_07]], i64 2
-; CHECK-NEXT: store i16 [[TMP11]], ptr [[PDST_ADDR_07]], align 2
+; CHECK-NEXT: store i16 [[TMP9]], ptr [[PDST_ADDR_07]], align 2
; CHECK-NEXT: [[DEC]] = add i32 [[BLKCNT_09]], -1
; CHECK-NEXT: [[CMP_NOT:%.*]] = icmp eq i32 [[DEC]], 0
; CHECK-NEXT: br i1 [[CMP_NOT]], label [[WHILE_END]], label [[WHILE_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
@@ -136,45 +136,45 @@ define void @umin(ptr nocapture readonly %pSrc, i8 signext %offset, ptr nocaptur
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N_VEC]], [[TMP0]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[WHILE_END]], label [[VEC_EPILOG_ITER_CHECK:%.*]]
; CHECK: vec.epilog.iter.check:
-; CHECK-NEXT: [[IND_END18:%.*]] = getelementptr i8, ptr [[PDST]], i64 [[N_VEC]]
-; CHECK-NEXT: [[IND_END15:%.*]] = getelementptr i8, ptr [[PSRC]], i64 [[N_VEC]]
-; CHECK-NEXT: [[DOTCAST11:%.*]] = trunc nuw i64 [[N_VEC]] to i32
-; CHECK-NEXT: [[IND_END12:%.*]] = sub i32 [[BLOCKSIZE]], [[DOTCAST11]]
+; CHECK-NEXT: [[IND_END14:%.*]] = getelementptr i8, ptr [[PDST]], i64 [[N_VEC]]
+; CHECK-NEXT: [[IND_END11:%.*]] = getelementptr i8, ptr [[PSRC]], i64 [[N_VEC]]
+; CHECK-NEXT: [[DOTCAST8:%.*]] = trunc nuw i64 [[N_VEC]] to i32
+; CHECK-NEXT: [[IND_END9:%.*]] = sub i32 [[BLOCKSIZE]], [[DOTCAST8]]
; CHECK-NEXT: [[N_VEC_REMAINING:%.*]] = and i64 [[TMP0]], 24
; CHECK-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp eq i64 [[N_VEC_REMAINING]], 0
; CHECK-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]]
; CHECK: vec.epilog.ph:
; CHECK-NEXT: [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
-; CHECK-NEXT: [[N_VEC9:%.*]] = and i64 [[TMP0]], 4294967288
-; CHECK-NEXT: [[DOTCAST:%.*]] = trunc nuw i64 [[N_VEC9]] to i32
-; CHECK-NEXT: [[IND_END10:%.*]] = sub i32 [[BLOCKSIZE]], [[DOTCAST]]
-; CHECK-NEXT: [[IND_END14:%.*]] = getelementptr i8, ptr [[PSRC]], i64 [[N_VEC9]]
-; CHECK-NEXT: [[IND_END17:%.*]] = getelementptr i8, ptr [[PDST]], i64 [[N_VEC9]]
-; CHECK-NEXT: [[BROADCAST_SPLATINSERT25:%.*]] = insertelement <8 x i8> poison, i8 [[OFFSET]], i64 0
-; CHECK-NEXT: [[BROADCAST_SPLAT26:%.*]] = shufflevector <8 x i8> [[BROADCAST_SPLATINSERT25]], <8 x i8> poison, <8 x i32> zeroinitializer
+; CHECK-NEXT: [[N_VEC7:%.*]] = and i64 [[TMP0]], 4294967288
+; CHECK-NEXT: [[DOTCAST:%.*]] = trunc nuw i64 [[N_VEC7]] to i32
+; CHECK-NEXT: [[IND_END:%.*]] = sub i32 [[BLOCKSIZE]], [[DOTCAST]]
+; CHECK-NEXT: [[IND_END10:%.*]] = getelementptr i8, ptr [[PSRC]], i64 [[N_VEC7]]
+; CHECK-NEXT: [[IND_END13:%.*]] = getelementptr i8, ptr [[PDST]], i64 [[N_VEC7]]
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT20:%.*]] = insertelement <8 x i8> poison, i8 [[OFFSET]], i64 0
+; CHECK-NEXT: [[BROADCAST_SPLAT21:%.*]] = shufflevector <8 x i8> [[BROADCAST_SPLATINSERT20]], <8 x i8> poison, <8 x i32> zeroinitializer
; CHECK-NEXT: br label [[VEC_EPILOG_VECTOR_BODY:%.*]]
; CHECK: vec.epilog.vector.body:
-; CHECK-NEXT: [[INDEX21:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT27:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
-; CHECK-NEXT: [[NEXT_GEP22:%.*]] = getelementptr i8, ptr [[PSRC]], i64 [[INDEX21]]
-; CHECK-NEXT: [[NEXT_GEP23:%.*]] = getelementptr i8, ptr [[PDST]], i64 [[INDEX21]]
-; CHECK-NEXT: [[WIDE_LOAD24:%.*]] = load <8 x i8>, ptr [[NEXT_GEP22]], align 2
-; CHECK-NEXT: [[TMP6:%.*]] = call <8 x i8> @llvm.umin.v8i8(<8 x i8> [[WIDE_LOAD24]], <8 x i8> [[BROADCAST_SPLAT26]])
-; CHECK-NEXT: store <8 x i8> [[TMP6]], ptr [[NEXT_GEP23]], align 2
-; CHECK-NEXT: [[INDEX_NEXT27]] = add nuw i64 [[INDEX21]], 8
-; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT27]], [[N_VEC9]]
+; CHECK-NEXT: [[INDEX16:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT22:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
+; CHECK-NEXT: [[NEXT_GEP17:%.*]] = getelementptr i8, ptr [[PSRC]], i64 [[INDEX16]]
+; CHECK-NEXT: [[NEXT_GEP18:%.*]] = getelementptr i8, ptr [[PDST]], i64 [[INDEX16]]
+; CHECK-NEXT: [[WIDE_LOAD19:%.*]] = load <8 x i8>, ptr [[NEXT_GEP17]], align 2
+; CHECK-NEXT: [[TMP6:%.*]] = call <8 x i8> @llvm.umin.v8i8(<8 x i8> [[WIDE_LOAD19]], <8 x i8> [[BROADCAST_SPLAT21]])
+; CHECK-NEXT: store <8 x i8> [[TMP6]], ptr [[NEXT_GEP18]], align 2
+; CHECK-NEXT: [[INDEX_NEXT22]] = add nuw i64 [[INDEX16]], 8
+; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT22]], [[N_VEC7]]
; CHECK-NEXT: br i1 [[TMP7]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK: vec.epilog.middle.block:
-; CHECK-NEXT: [[CMP_N20:%.*]] = icmp eq i64 [[N_VEC9]], [[TMP0]]
-; CHECK-NEXT: br i1 [[CMP_N20]], label [[WHILE_END]], label [[VEC_EPILOG_SCALAR_PH]]
+; CHECK-NEXT: [[CMP_N23:%.*]] = icmp eq i64 [[N_VEC7]], [[TMP0]]
+; CHECK-NEXT: br i1 [[CMP_N23]], label [[WHILE_END]], label [[VEC_EPILOG_SCALAR_PH]]
; CHECK: vec.epilog.scalar.ph:
-; CHECK-NEXT: [[BC_RESUME_VAL13:%.*]] = phi i32 [ [[IND_END10]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[IND_END12]], [[VEC_EPILOG_ITER_CHECK]] ], [ [[BLOCKSIZE]], [[ITER_CHECK]] ]
-; CHECK-NEXT: [[BC_RESUME_VAL16:%.*]] = phi ptr [ [[IND_END14]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[IND_END15]], [[VEC_EPILOG_ITER_CHECK]] ], [ [[PSRC]], [[ITER_CHECK]] ]
-; CHECK-NEXT: [[BC_RESUME_VAL19:%.*]] = phi ptr [ [[IND_END17]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[IND_END18]], [[VEC_EPILOG_ITER_CHECK]] ], [ [[PDST]], [[ITER_CHECK]] ]
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ [[IND_END]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[IND_END9]], [[VEC_EPILOG_ITER_CHECK]] ], [ [[BLOCKSIZE]], [[ITER_CHECK]] ]
+; CHECK-NEXT: [[BC_RESUME_VAL12:%.*]] = phi ptr [ [[IND_END10]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[IND_END11]], [[VEC_EPILOG_ITER_CHECK]] ], [ [[PSRC]], [[ITER_CHECK]] ]
+; CHECK-NEXT: [[BC_RESUME_VAL15:%.*]] = phi ptr [ [[IND_END13]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[IND_END14]], [[VEC_EPILOG_ITER_CHECK]] ], [ [[PDST]], [[ITER_CHECK]] ]
; CHECK-NEXT: br label [[WHILE_BODY:%.*]]
; CHECK: while.body:
-; CHECK-NEXT: [[BLKCNT_09:%.*]] = phi i32 [ [[DEC:%.*]], [[WHILE_BODY]] ], [ [[BC_RESUME_VAL13]], [[VEC_EPILOG_SCALAR_PH]] ]
-; CHECK-NEXT: [[PSRC_ADDR_08:%.*]] = phi ptr [ [[INCDEC_PTR:%.*]], [[WHILE_BODY]] ], [ [[BC_RESUME_VAL16]], [[VEC_EPILOG_SCALAR_PH]] ]
-; CHECK-NEXT: [[PDST_ADDR_07:%.*]] = phi ptr [ [[INCDEC_PTR3:%.*]], [[WHILE_BODY]] ], [ [[BC_RESUME_VAL19]], [[VEC_EPILOG_SCALAR_PH]] ]
+; CHECK-NEXT: [[BLKCNT_09:%.*]] = phi i32 [ [[DEC:%.*]], [[WHILE_BODY]] ], [ [[BC_RESUME_VAL]], [[VEC_EPILOG_SCALAR_PH]] ]
+; CHECK-NEXT: [[PSRC_ADDR_08:%.*]] = phi ptr [ [[INCDEC_PTR:%.*]], [[WHILE_BODY]] ], [ [[BC_RESUME_VAL12]], [[VEC_EPILOG_SCALAR_PH]] ]
+; CHECK-NEXT: [[PDST_ADDR_07:%.*]] = phi ptr [ [[INCDEC_PTR3:%.*]], [[WHILE_BODY]] ], [ [[BC_RESUME_VAL15]], [[VEC_EPILOG_SCALAR_PH]] ]
; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds i8, ptr [[PSRC_ADDR_08]], i64 1
; CHECK-NEXT: [[TMP8:%.*]] = load i8, ptr [[PSRC_ADDR_08]], align 2
; CHECK-NEXT: [[TMP9:%.*]] = tail call i8 @llvm.umin.i8(i8 [[TMP8]], i8 [[OFFSET]])
diff --git a/llvm/test/Transforms/LoopVectorize/ARM/mve-saddsatcost.ll b/llvm/test/Transforms/LoopVectorize/ARM/mve-saddsatcost.ll
index 44d17d09307b3..a787ce512f653 100644
--- a/llvm/test/Transforms/LoopVectorize/ARM/mve-saddsatcost.ll
+++ b/llvm/test/Transforms/LoopVectorize/ARM/mve-saddsatcost.ll
@@ -8,7 +8,7 @@ target triple = "thumbv8.1m.main-arm-none-eabi"
; CHECK-COST-LABEL: arm_offset_q15
; CHECK-COST: Found an estimated cost of 1 for VF 1 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
-; CHECK-COST: Found an estimated cost of 26 for VF 2 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
+; CHECK-COST: Found an estimated cost of 36 for VF 2 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
; CHECK-COST: Found an estimated cost of 8 for VF 4 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
; CHECK-COST: Found an estimated cost of 2 for VF 8 For instruction: %1 = tail call i16 @llvm.sadd.sat.i16(i16 %0, i16 %offset)
@@ -20,22 +20,22 @@ define void @arm_offset_q15(ptr nocapture readonly %pSrc, i16 signext %offset, p
; CHECK: vector.ph:
; CHECK-NEXT: [[N_RND_UP:%.*]] = add i32 [[BLOCKSIZE]], 7
; CHECK-NEXT: [[N_VEC:%.*]] = and i32 [[N_RND_UP]], -8
-; CHECK-NEXT: [[BROADCAST_SPLATINSERT6:%.*]] = insertelement <8 x i16> poison, i16 [[OFFSET:%.*]], i64 0
-; CHECK-NEXT: [[BROADCAST_SPLAT7:%.*]] = shufflevector <8 x i16> [[BROADCAST_SPLATINSERT6]], <8 x i16> poison, <8 x i32> zeroinitializer
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT7:%.*]] = insertelement <8 x i16> poison, i16 [[OFFSET:%.*]], i64 0
+; CHECK-NEXT: [[BROADCAST_SPLAT8:%.*]] = shufflevector <8 x i16> [[BROADCAST_SPLATINSERT7]], <8 x i16> poison, <8 x i32> zeroinitializer
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[TMP0:%.*]] = shl i32 [[INDEX]], 1
-; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[PSRC:%.*]], i32 [[TMP0]]
-; CHECK-NEXT: [[TMP1:%.*]] = shl i32 [[INDEX]], 1
-; CHECK-NEXT: [[NEXT_GEP5:%.*]] = getelementptr i8, ptr [[PDST:%.*]], i32 [[TMP1]]
+; CHECK-NEXT: [[OFFSET_IDX:%.*]] = shl i32 [[INDEX]], 1
+; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[PSRC:%.*]], i32 [[OFFSET_IDX]]
+; CHECK-NEXT: [[OFFSET_IDX5:%.*]] = shl i32 [[INDEX]], 1
+; CHECK-NEXT: [[NEXT_GEP6:%.*]] = getelementptr i8, ptr [[PDST:%.*]], i32 [[OFFSET_IDX5]]
; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 [[INDEX]], i32 [[BLOCKSIZE]])
; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <8 x i16> @llvm.masked.load.v8i16.p0(ptr [[NEXT_GEP]], i32 2, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i16> poison)
-; CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> [[WIDE_MASKED_LOAD]], <8 x i16> [[BROADCAST_SPLAT7]])
-; CHECK-NEXT: call void @llvm.masked.store.v8i16.p0(<8 x i16> [[TMP2]], ptr [[NEXT_GEP5]], i32 2, <8 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> [[WIDE_MASKED_LOAD]], <8 x i16> [[BROADCAST_SPLAT8]])
+; CHECK-NEXT: call void @llvm.masked.store.v8i16.p0(<8 x i16> [[TMP0]], ptr [[NEXT_GEP6]], i32 2, <8 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 8
-; CHECK-NEXT: [[TMP3:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP3]], label [[WHILE_END]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-NEXT: [[TMP1:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[TMP1]], label [[WHILE_END]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: while.end:
; CHECK-NEXT: ret void
;
>From ae93c8878cbf32c81aa5c0b375fc4dcf6ec71474 Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault at amd.com>
Date: Thu, 25 Jul 2024 09:56:59 +0400
Subject: [PATCH 5/5] Use switch
---
llvm/include/llvm/CodeGen/BasicTTIImpl.h | 22 ++++++++++++++--------
1 file changed, 14 insertions(+), 8 deletions(-)
diff --git a/llvm/include/llvm/CodeGen/BasicTTIImpl.h b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
index 2d2efc877024e..f9fc02b332b00 100644
--- a/llvm/include/llvm/CodeGen/BasicTTIImpl.h
+++ b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
@@ -2323,14 +2323,17 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
return (LT.first * 2);
}
- // If we can't lower fmuladd into an FMA estimate the cost as a floating
- // point mul followed by an add.
- if (IID == Intrinsic::fmuladd)
+ switch (IID) {
+ case Intrinsic::fmuladd: {
+ // If we can't lower fmuladd into an FMA estimate the cost as a floating
+ // point mul followed by an add.
+
return thisT()->getArithmeticInstrCost(BinaryOperator::FMul, RetTy,
CostKind) +
thisT()->getArithmeticInstrCost(BinaryOperator::FAdd, RetTy,
CostKind);
- if (IID == Intrinsic::experimental_constrained_fmuladd) {
+ }
+ case Intrinsic::experimental_constrained_fmuladd: {
IntrinsicCostAttributes FMulAttrs(
Intrinsic::experimental_constrained_fmul, RetTy, Tys);
IntrinsicCostAttributes FAddAttrs(
@@ -2338,8 +2341,8 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
return thisT()->getIntrinsicInstrCost(FMulAttrs, CostKind) +
thisT()->getIntrinsicInstrCost(FAddAttrs, CostKind);
}
-
- if (IID == Intrinsic::sadd_sat || IID == Intrinsic::ssub_sat) {
+ case Intrinsic::sadd_sat:
+ case Intrinsic::ssub_sat: {
// Assume a default expansion.
Type *CondTy = RetTy->getWithNewBitWidth(1);
@@ -2361,8 +2364,8 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
CondTy, Pred, CostKind);
return Cost;
}
-
- if (IID == Intrinsic::uadd_sat || IID == Intrinsic::usub_sat) {
+ case Intrinsic::uadd_sat:
+ case Intrinsic::usub_sat: {
Type *CondTy = RetTy->getWithNewBitWidth(1);
Type *OpTy = StructType::create({RetTy, CondTy});
@@ -2379,6 +2382,9 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
CmpInst::BAD_ICMP_PREDICATE, CostKind);
return Cost;
}
+ default:
+ break;
+ }
// Else, assume that we need to scalarize this intrinsic. For math builtins
// this will emit a costly libcall, adding call overhead and spills. Make it
More information about the llvm-commits
mailing list