[llvm] [LV] Pre-commit test for #151664 (PR #151671)
Ramkumar Ramachandra via llvm-commits
llvm-commits at lists.llvm.org
Fri Aug 1 02:15:55 PDT 2025
https://github.com/artagnon updated https://github.com/llvm/llvm-project/pull/151671
>From 4b7c0f536264c57834b7b858670a98a3319c663d Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <ramkumar.ramachandra at codasip.com>
Date: Fri, 1 Aug 2025 09:25:12 +0100
Subject: [PATCH 1/2] [LV] Pre-commit test for #151664
Hoisted vector instructions are costed incorrectly.
---
.../Analysis/CostModel/AArch64/min-max.ll | 77 +++++++++++++++++++
.../Analysis/CostModel/AArch64/sve-min-max.ll | 71 +++++++++++++++++
.../pr151664-cost-hoisted-vector-scalable.ll | 62 +++++++++++++++
3 files changed, 210 insertions(+)
create mode 100644 llvm/test/Transforms/LoopVectorize/AArch64/pr151664-cost-hoisted-vector-scalable.ll
diff --git a/llvm/test/Analysis/CostModel/AArch64/min-max.ll b/llvm/test/Analysis/CostModel/AArch64/min-max.ll
index b824f5309adc1..3c052b1eeea82 100644
--- a/llvm/test/Analysis/CostModel/AArch64/min-max.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/min-max.ll
@@ -377,6 +377,66 @@ define void @maximum() {
ret void
}
+define void @minimumnum() {
+; CHECK-LABEL: 'minimumnum'
+; CHECK-NEXT: Cost Model: Found costs of 3 for: %1 = call <2 x float> @llvm.minimumnum.v2f32(<2 x float> poison, <2 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of 3 for: %2 = call <4 x float> @llvm.minimumnum.v4f32(<4 x float> poison, <4 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of 10 for: %3 = call <8 x float> @llvm.minimumnum.v8f32(<8 x float> poison, <8 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of 20 for: %4 = call <16 x float> @llvm.minimumnum.v16f32(<16 x float> poison, <16 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of 3 for: %5 = call <2 x double> @llvm.minimumnum.v2f64(<2 x double> poison, <2 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of 10 for: %6 = call <4 x double> @llvm.minimumnum.v4f64(<4 x double> poison, <4 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of 20 for: %7 = call <8 x double> @llvm.minimumnum.v8f64(<8 x double> poison, <8 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of 40 for: %8 = call <16 x double> @llvm.minimumnum.v16f64(<16 x double> poison, <16 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ call <2 x float> @llvm.minimumnum.v2f32(<2 x float> poison, <2 x float> poison)
+ call <4 x float> @llvm.minimumnum.v4f32(<4 x float> poison, <4 x float> poison)
+ call <8 x float> @llvm.minimumnum.v8f32(<8 x float> poison, <8 x float> poison)
+ call <16 x float> @llvm.minimumnum.v16f32(<16 x float> poison, <16 x float> poison)
+ call <2 x double> @llvm.minimumnum.v2f64(<2 x double> poison, <2 x double> poison)
+ call <4 x double> @llvm.minimumnum.v4f64(<4 x double> poison, <4 x double> poison)
+ call <8 x double> @llvm.minimumnum.v8f64(<8 x double> poison, <8 x double> poison)
+ call <16 x double> @llvm.minimumnum.v16f64(<16 x double> poison, <16 x double> poison)
+ ret void
+}
+
+define void @minimumnum_fp16() {
+; CHECK-NOF16-LABEL: 'minimumnum_fp16'
+; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:4 CodeSize:3 Lat:4 SizeLat:4 for: %1 = call <2 x half> @llvm.minimumnum.v2f16(<2 x half> poison, <2 x half> poison)
+; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:10 CodeSize:7 Lat:10 SizeLat:10 for: %2 = call <4 x half> @llvm.minimumnum.v4f16(<4 x half> poison, <4 x half> poison)
+; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:22 CodeSize:15 Lat:22 SizeLat:22 for: %3 = call <8 x half> @llvm.minimumnum.v8f16(<8 x half> poison, <8 x half> poison)
+; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:44 CodeSize:30 Lat:44 SizeLat:44 for: %4 = call <16 x half> @llvm.minimumnum.v16f16(<16 x half> poison, <16 x half> poison)
+; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+; CHECK-F16-LABEL: 'minimumnum_fp16'
+; CHECK-F16-NEXT: Cost Model: Found costs of 3 for: %1 = call <2 x half> @llvm.minimumnum.v2f16(<2 x half> poison, <2 x half> poison)
+; CHECK-F16-NEXT: Cost Model: Found costs of 3 for: %2 = call <4 x half> @llvm.minimumnum.v4f16(<4 x half> poison, <4 x half> poison)
+; CHECK-F16-NEXT: Cost Model: Found costs of 3 for: %3 = call <8 x half> @llvm.minimumnum.v8f16(<8 x half> poison, <8 x half> poison)
+; CHECK-F16-NEXT: Cost Model: Found costs of 10 for: %4 = call <16 x half> @llvm.minimumnum.v16f16(<16 x half> poison, <16 x half> poison)
+; CHECK-F16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ call <2 x half> @llvm.minimumnum.v2f16(<2 x half> poison, <2 x half> poison)
+ call <4 x half> @llvm.minimumnum.v4f16(<4 x half> poison, <4 x half> poison)
+ call <8 x half> @llvm.minimumnum.v8f16(<8 x half> poison, <8 x half> poison)
+ call <16 x half> @llvm.minimumnum.v16f16(<16 x half> poison, <16 x half> poison)
+ ret void
+}
+
+define void @minimumnum_bf16() {
+; CHECK-LABEL: 'minimumnum_bf16'
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:3 Lat:4 SizeLat:4 for: %1 = call <2 x bfloat> @llvm.minimumnum.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:7 Lat:10 SizeLat:10 for: %2 = call <4 x bfloat> @llvm.minimumnum.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of RThru:22 CodeSize:15 Lat:22 SizeLat:22 for: %3 = call <8 x bfloat> @llvm.minimumnum.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of RThru:44 CodeSize:30 Lat:44 SizeLat:44 for: %4 = call <16 x bfloat> @llvm.minimumnum.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ call <2 x bfloat> @llvm.minimumnum.v2fb16(<2 x bfloat> poison, <2 x bfloat> poison)
+ call <4 x bfloat> @llvm.minimumnum.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison)
+ call <8 x bfloat> @llvm.minimumnum.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison)
+ call <16 x bfloat> @llvm.minimumnum.v6bf16(<16 x bfloat> poison, <16 x bfloat> poison)
+ ret void
+}
+
declare i8 @llvm.umin.i8(i8, i8)
declare i16 @llvm.umin.i16(i16, i16)
declare i32 @llvm.umin.i32(i32, i32)
@@ -512,3 +572,20 @@ declare <4 x float> @llvm.maximum.v4f32(<4 x float>, <4 x float>)
declare <8 x float> @llvm.maximum.v8f32(<8 x float>, <8 x float>)
declare <2 x double> @llvm.maximum.v2f64(<2 x double>, <2 x double>)
declare <4 x double> @llvm.maximum.v4f64(<4 x double>, <4 x double>)
+
+declare <2 x half> @llvm.minimumnum.v2f16(<2 x half>, <2 x half>)
+declare <4 x half> @llvm.minimumnum.v4f16(<4 x half>, <4 x half>)
+declare <8 x half> @llvm.minimumnum.v8f16(<8 x half>, <8 x half>)
+declare <16 x half> @llvm.minimumnum.v16f16(<16 x half>, <16 x half>)
+declare <2 x bfloat> @llvm.minimumnum.2bf16(<2 x bfloat>, <2 x bfloat>)
+declare <4 x bfloat> @llvm.minimumnum.4bf16(<4 x bfloat>, <4 x bfloat>)
+declare <8 x bfloat> @llvm.minimumnum.v8bf16(<8 x bfloat>, <8 x bfloat>)
+declare <16 x bfloat> @llvm.minimumnum.v16bf16(<16 x bfloat>, <16 x bfloat>)
+declare <2 x float> @llvm.minimumnum.v2f32(<2 x float>, <2 x float>)
+declare <4 x float> @llvm.minimumnum.v4f32(<4 x float>, <4 x float>)
+declare <8 x float> @llvm.minimumnum.v8f32(<8 x float>, <8 x float>)
+declare <16 x float> @llvm.minimumnum.v16f32(<16 x float>, <16 x float>)
+declare <2 x double> @llvm.minimumnum.v2f64(<2 x double>, <2 x double>)
+declare <4 x double> @llvm.minimumnum.v4f64(<4 x double>, <4 x double>)
+declare <8 x double> @llvm.minimumnum.nxv8f64(<8 x double>, <8 x double>)
+declare <16 x double> @llvm.minimumnum.nxv16f64(<16 x double>, <16 x double>)
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll b/llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll
index 829ce127493ed..73574dd61d75c 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll
@@ -255,6 +255,60 @@ define void @maximum() {
ret void
}
+define void @minimumnum() {
+; CHECK-LABEL: 'minimumnum'
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %1 = call <vscale x 2 x float> @llvm.minimumnum.nxv2f32(<vscale x 2 x float> poison, <vscale x 2 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %2 = call <vscale x 4 x float> @llvm.minimumnum.nxv4f32(<vscale x 4 x float> poison, <vscale x 4 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %3 = call <vscale x 8 x float> @llvm.minimumnum.nxv8f32(<vscale x 8 x float> poison, <vscale x 8 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %4 = call <vscale x 16 x float> @llvm.minimumnum.nxv16f32(<vscale x 16 x float> poison, <vscale x 16 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %5 = call <vscale x 2 x double> @llvm.minimumnum.nxv2f64(<vscale x 2 x double> poison, <vscale x 2 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %6 = call <vscale x 4 x double> @llvm.minimumnum.nxv4f64(<vscale x 4 x double> poison, <vscale x 4 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %7 = call <vscale x 8 x double> @llvm.minimumnum.nxv8f64(<vscale x 8 x double> poison, <vscale x 8 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %8 = call <vscale x 16 x double> @llvm.minimumnum.nxv16f64(<vscale x 16 x double> poison, <vscale x 16 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ call <vscale x 2 x float> @llvm.minimumnum(<vscale x 2 x float> poison, <vscale x 2 x float> poison)
+ call <vscale x 4 x float> @llvm.minimumnum(<vscale x 4 x float> poison, <vscale x 4 x float> poison)
+ call <vscale x 8 x float> @llvm.minimumnum(<vscale x 8 x float> poison, <vscale x 8 x float> poison)
+ call <vscale x 16 x float> @llvm.minimumnum(<vscale x 16 x float> poison, <vscale x 16 x float> poison)
+ call <vscale x 2 x double> @llvm.minimumnum(<vscale x 2 x double> poison, <vscale x 2 x double> poison)
+ call <vscale x 4 x double> @llvm.minimumnum(<vscale x 4 x double> poison, <vscale x 4 x double> poison)
+ call <vscale x 8 x double> @llvm.minimumnum(<vscale x 8 x double> poison, <vscale x 8 x double> poison)
+ call <vscale x 16 x double> @llvm.minimumnum(<vscale x 16 x double> poison, <vscale x 16 x double> poison)
+ ret void
+}
+
+define void @minimumnum_fp16() {
+; CHECK-LABEL: 'minimumnum_fp16'
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %1 = call <vscale x 2 x half> @llvm.minimumnum.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %2 = call <vscale x 4 x half> @llvm.minimumnum.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %3 = call <vscale x 8 x half> @llvm.minimumnum.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %4 = call <vscale x 16 x half> @llvm.minimumnum.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ call <vscale x 2 x half> @llvm.minimumnum(<vscale x 2 x half> poison, <vscale x 2 x half> poison)
+ call <vscale x 4 x half> @llvm.minimumnum(<vscale x 4 x half> poison, <vscale x 4 x half> poison)
+ call <vscale x 8 x half> @llvm.minimumnum(<vscale x 8 x half> poison, <vscale x 8 x half> poison)
+ call <vscale x 16 x half> @llvm.minimumnum(<vscale x 16 x half> poison, <vscale x 16 x half> poison)
+ ret void
+}
+
+define void @minimumnum_bf16() {
+; CHECK-LABEL: 'minimumnum_bf16'
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %1 = call <vscale x 2 x bfloat> @llvm.minimumnum.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %2 = call <vscale x 4 x bfloat> @llvm.minimumnum.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %3 = call <vscale x 8 x bfloat> @llvm.minimumnum.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %4 = call <vscale x 16 x bfloat> @llvm.minimumnum.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ call <vscale x 2 x bfloat> @llvm.minimumnum(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison)
+ call <vscale x 4 x bfloat> @llvm.minimumnum(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison)
+ call <vscale x 8 x bfloat> @llvm.minimumnum(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison)
+ call <vscale x 16 x bfloat> @llvm.minimumnum(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison)
+ ret void
+}
+
+
declare <vscale x 4 x i8> @llvm.umin.nxv4i8(<vscale x 4 x i8>, <vscale x 4 x i8>)
declare <vscale x 8 x i8> @llvm.umin.nxv8i8(<vscale x 8 x i8>, <vscale x 8 x i8>)
declare <vscale x 16 x i8> @llvm.umin.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
@@ -354,3 +408,20 @@ declare <vscale x 4 x float> @llvm.maximum.nxv4f32(<vscale x 4 x float>, <vscale
declare <vscale x 8 x float> @llvm.maximum.nxv8f32(<vscale x 8 x float>, <vscale x 8 x float>)
declare <vscale x 2 x double> @llvm.maximum.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 4 x double> @llvm.maximum.nxv4f64(<vscale x 4 x double>, <vscale x 4 x double>)
+
+declare <vscale x 2 x half> @llvm.minimumnum.nxv2f16(<vscale x 2 x half>, <vscale x 2 x half>)
+declare <vscale x 4 x half> @llvm.minimumnum.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>)
+declare <vscale x 8 x half> @llvm.minimumnum.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
+declare <vscale x 16 x half> @llvm.minimumnum.nxv16f16(<vscale x 16 x half>, <vscale x 16 x half>)
+declare <vscale x 2 x bfloat> @llvm.minimumnum.nxv2bf16(<vscale x 2 x bfloat>, <vscale x 2 x bfloat>)
+declare <vscale x 4 x bfloat> @llvm.minimumnum.nxv4bf16(<vscale x 4 x bfloat>, <vscale x 4 x bfloat>)
+declare <vscale x 8 x bfloat> @llvm.minimumnum.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
+declare <vscale x 16 x bfloat> @llvm.minimumnum.nxv16bf16(<vscale x 16 x bfloat>, <vscale x 16 x bfloat>)
+declare <vscale x 2 x float> @llvm.minimumnum.nxv2f32(<vscale x 2 x float>, <vscale x 2 x float>)
+declare <vscale x 4 x float> @llvm.minimumnum.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 8 x float> @llvm.minimumnum.nxv8f32(<vscale x 8 x float>, <vscale x 8 x float>)
+declare <vscale x 16 x float> @llvm.minimumnum.nxv16f32(<vscale x 16 x float>, <vscale x 16 x float>)
+declare <vscale x 2 x double> @llvm.minimumnum.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
+declare <vscale x 4 x double> @llvm.minimumnum.nxv4f64(<vscale x 4 x double>, <vscale x 4 x double>)
+declare <vscale x 8 x double> @llvm.minimumnum.nxv8f64(<vscale x 8 x double>, <vscale x 8 x double>)
+declare <vscale x 16 x double> @llvm.minimumnum.nxv16f64(<vscale x 16 x double>, <vscale x 16 x double>)
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/pr151664-cost-hoisted-vector-scalable.ll b/llvm/test/Transforms/LoopVectorize/AArch64/pr151664-cost-hoisted-vector-scalable.ll
new file mode 100644
index 0000000000000..2823712c9143a
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/pr151664-cost-hoisted-vector-scalable.ll
@@ -0,0 +1,62 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --filter-out-after "^scalar.ph" --version 5
+; RUN: opt -passes=loop-vectorize -mtriple=aarch64 -mattr=+sve -S \
+; RUN: -debug-only=loop-vectorize %s 2>&1 | FileCheck %s
+
+; FIXME: Hoisted vector code should be costed with scalable cost.
+; In this example, `<vscale x 4 x float> @llvm.minimumnum` has an invalid cost,
+; and hence should not be produced by LoopVectorize. Unfortunately, what is
+; actually costed is `<4 x float> @llvm.minimumnum`.
+
+; CHECK: LV: Found an estimated cost of 3 for VF 1 For instruction: %res = tail call float @llvm.minimumnum.f32(float 0.000000e+00, float 0.000000e+00)
+define void @cost_hoisted_vector_code(ptr %p) {
+; CHECK-LABEL: define void @cost_hoisted_vector_code(
+; CHECK-SAME: ptr [[P:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP1:%.*]] = mul nuw i64 [[TMP0]], 8
+; CHECK-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 8
+; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 -1, [[TMP3]]
+; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 -1, [[N_MOD_VF]]
+; CHECK-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 8
+; CHECK-NEXT: [[TMP6:%.*]] = add i64 1, [[N_VEC]]
+; CHECK-NEXT: [[TMP7:%.*]] = call <vscale x 4 x float> @llvm.minimumnum.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer)
+; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
+; CHECK: [[VECTOR_BODY]]:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[TMP8:%.*]] = getelementptr float, ptr [[P]], i64 [[INDEX]]
+; CHECK-NEXT: [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP10:%.*]] = mul nuw i64 [[TMP9]], 4
+; CHECK-NEXT: [[TMP11:%.*]] = getelementptr float, ptr [[TMP8]], i64 [[TMP10]]
+; CHECK-NEXT: store <vscale x 4 x float> [[TMP7]], ptr [[TMP8]], align 4
+; CHECK-NEXT: store <vscale x 4 x float> [[TMP7]], ptr [[TMP11]], align 4
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
+; CHECK-NEXT: [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[TMP12]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 -1, [[N_VEC]]
+; CHECK-NEXT: br i1 [[CMP_N]], [[EXIT:label %.*]], label %[[SCALAR_PH]]
+; CHECK: [[SCALAR_PH]]:
+;
+entry:
+ br label %loop
+
+loop: ; preds = %loop, %entry
+ %iv = phi i64 [ 1, %entry ], [ %iv.next, %loop ]
+ %idx = phi i64 [ 0, %entry ], [ %idx.next, %loop ]
+ %res = tail call float @llvm.minimumnum.f32(float 0.0, float 0.0)
+ %gep.p.red = getelementptr float, ptr %p, i64 %idx
+ store float %res, ptr %gep.p.red, align 4
+ %idx.next = add i64 %idx, 1
+ %iv.next = add i64 %iv, 1
+ %exit.cond = icmp eq i64 %iv.next, 0
+ br i1 %exit.cond, label %exit, label %loop
+
+exit: ; preds = %loop
+ ret void
+}
+
+declare float @llvm.minimumnum.f32(float, float)
>From e44e014113ce1eb281d583e9cdc0141bc56c5630 Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <ramkumar.ramachandra at codasip.com>
Date: Fri, 1 Aug 2025 10:12:12 +0100
Subject: [PATCH 2/2] [CostModel, LV] Address review
---
.../Analysis/CostModel/AArch64/min-max.ll | 101 +++++++++++++-----
.../Analysis/CostModel/AArch64/sve-min-max.ll | 86 ++++++++-------
.../pr151664-cost-hoisted-vector-scalable.ll | 12 ++-
3 files changed, 132 insertions(+), 67 deletions(-)
diff --git a/llvm/test/Analysis/CostModel/AArch64/min-max.ll b/llvm/test/Analysis/CostModel/AArch64/min-max.ll
index 3c052b1eeea82..9b0ae9e55f448 100644
--- a/llvm/test/Analysis/CostModel/AArch64/min-max.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/min-max.ll
@@ -379,16 +379,20 @@ define void @maximum() {
define void @minimumnum() {
; CHECK-LABEL: 'minimumnum'
-; CHECK-NEXT: Cost Model: Found costs of 3 for: %1 = call <2 x float> @llvm.minimumnum.v2f32(<2 x float> poison, <2 x float> poison)
-; CHECK-NEXT: Cost Model: Found costs of 3 for: %2 = call <4 x float> @llvm.minimumnum.v4f32(<4 x float> poison, <4 x float> poison)
-; CHECK-NEXT: Cost Model: Found costs of 10 for: %3 = call <8 x float> @llvm.minimumnum.v8f32(<8 x float> poison, <8 x float> poison)
-; CHECK-NEXT: Cost Model: Found costs of 20 for: %4 = call <16 x float> @llvm.minimumnum.v16f32(<16 x float> poison, <16 x float> poison)
-; CHECK-NEXT: Cost Model: Found costs of 3 for: %5 = call <2 x double> @llvm.minimumnum.v2f64(<2 x double> poison, <2 x double> poison)
-; CHECK-NEXT: Cost Model: Found costs of 10 for: %6 = call <4 x double> @llvm.minimumnum.v4f64(<4 x double> poison, <4 x double> poison)
-; CHECK-NEXT: Cost Model: Found costs of 20 for: %7 = call <8 x double> @llvm.minimumnum.v8f64(<8 x double> poison, <8 x double> poison)
-; CHECK-NEXT: Cost Model: Found costs of 40 for: %8 = call <16 x double> @llvm.minimumnum.v16f64(<16 x double> poison, <16 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of 3 for: %1 = call float @llvm.minimumnum.f32(float poison, float poison)
+; CHECK-NEXT: Cost Model: Found costs of 3 for: %2 = call double @llvm.minimumnum.f64(double poison, double poison)
+; CHECK-NEXT: Cost Model: Found costs of 3 for: %3 = call <2 x float> @llvm.minimumnum.v2f32(<2 x float> poison, <2 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of 3 for: %4 = call <4 x float> @llvm.minimumnum.v4f32(<4 x float> poison, <4 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of 10 for: %5 = call <8 x float> @llvm.minimumnum.v8f32(<8 x float> poison, <8 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of 20 for: %6 = call <16 x float> @llvm.minimumnum.v16f32(<16 x float> poison, <16 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of 3 for: %7 = call <2 x double> @llvm.minimumnum.v2f64(<2 x double> poison, <2 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of 10 for: %8 = call <4 x double> @llvm.minimumnum.v4f64(<4 x double> poison, <4 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of 20 for: %9 = call <8 x double> @llvm.minimumnum.v8f64(<8 x double> poison, <8 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of 40 for: %10 = call <16 x double> @llvm.minimumnum.v16f64(<16 x double> poison, <16 x double> poison)
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
+ call float @llvm.minimumnum.f32(float poison, float poison)
+ call double @llvm.minimumnum.f64(double poison, double poison)
call <2 x float> @llvm.minimumnum.v2f32(<2 x float> poison, <2 x float> poison)
call <4 x float> @llvm.minimumnum.v4f32(<4 x float> poison, <4 x float> poison)
call <8 x float> @llvm.minimumnum.v8f32(<8 x float> poison, <8 x float> poison)
@@ -437,6 +441,70 @@ define void @minimumnum_bf16() {
ret void
}
+define void @maximumnum() {
+; CHECK-LABEL: 'maximumnum'
+; CHECK-NEXT: Cost Model: Found costs of 3 for: %1 = call float @llvm.maximumnum.f32(float poison, float poison)
+; CHECK-NEXT: Cost Model: Found costs of 3 for: %2 = call double @llvm.maximumnum.f64(double poison, double poison)
+; CHECK-NEXT: Cost Model: Found costs of 3 for: %3 = call <2 x float> @llvm.maximumnum.v2f32(<2 x float> poison, <2 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of 3 for: %4 = call <4 x float> @llvm.maximumnum.v4f32(<4 x float> poison, <4 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of 10 for: %5 = call <8 x float> @llvm.maximumnum.v8f32(<8 x float> poison, <8 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of 20 for: %6 = call <16 x float> @llvm.maximumnum.v16f32(<16 x float> poison, <16 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of 3 for: %7 = call <2 x double> @llvm.maximumnum.v2f64(<2 x double> poison, <2 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of 10 for: %8 = call <4 x double> @llvm.maximumnum.v4f64(<4 x double> poison, <4 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of 20 for: %9 = call <8 x double> @llvm.maximumnum.v8f64(<8 x double> poison, <8 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of 40 for: %10 = call <16 x double> @llvm.maximumnum.v16f64(<16 x double> poison, <16 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ call float @llvm.maximumnum.f32(float poison, float poison)
+ call double @llvm.maximumnum.f64(double poison, double poison)
+ call <2 x float> @llvm.maximumnum.v2f32(<2 x float> poison, <2 x float> poison)
+ call <4 x float> @llvm.maximumnum.v4f32(<4 x float> poison, <4 x float> poison)
+ call <8 x float> @llvm.maximumnum.v8f32(<8 x float> poison, <8 x float> poison)
+ call <16 x float> @llvm.maximumnum.v16f32(<16 x float> poison, <16 x float> poison)
+ call <2 x double> @llvm.maximumnum.v2f64(<2 x double> poison, <2 x double> poison)
+ call <4 x double> @llvm.maximumnum.v4f64(<4 x double> poison, <4 x double> poison)
+ call <8 x double> @llvm.maximumnum.v8f64(<8 x double> poison, <8 x double> poison)
+ call <16 x double> @llvm.maximumnum.v16f64(<16 x double> poison, <16 x double> poison)
+ ret void
+}
+
+define void @maximumnum_fp16() {
+; CHECK-NOF16-LABEL: 'maximumnum_fp16'
+; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:4 CodeSize:3 Lat:4 SizeLat:4 for: %1 = call <2 x half> @llvm.maximumnum.v2f16(<2 x half> poison, <2 x half> poison)
+; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:10 CodeSize:7 Lat:10 SizeLat:10 for: %2 = call <4 x half> @llvm.maximumnum.v4f16(<4 x half> poison, <4 x half> poison)
+; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:22 CodeSize:15 Lat:22 SizeLat:22 for: %3 = call <8 x half> @llvm.maximumnum.v8f16(<8 x half> poison, <8 x half> poison)
+; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:44 CodeSize:30 Lat:44 SizeLat:44 for: %4 = call <16 x half> @llvm.maximumnum.v16f16(<16 x half> poison, <16 x half> poison)
+; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+; CHECK-F16-LABEL: 'maximumnum_fp16'
+; CHECK-F16-NEXT: Cost Model: Found costs of 3 for: %1 = call <2 x half> @llvm.maximumnum.v2f16(<2 x half> poison, <2 x half> poison)
+; CHECK-F16-NEXT: Cost Model: Found costs of 3 for: %2 = call <4 x half> @llvm.maximumnum.v4f16(<4 x half> poison, <4 x half> poison)
+; CHECK-F16-NEXT: Cost Model: Found costs of 3 for: %3 = call <8 x half> @llvm.maximumnum.v8f16(<8 x half> poison, <8 x half> poison)
+; CHECK-F16-NEXT: Cost Model: Found costs of 10 for: %4 = call <16 x half> @llvm.maximumnum.v16f16(<16 x half> poison, <16 x half> poison)
+; CHECK-F16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ call <2 x half> @llvm.maximumnum.v2f16(<2 x half> poison, <2 x half> poison)
+ call <4 x half> @llvm.maximumnum.v4f16(<4 x half> poison, <4 x half> poison)
+ call <8 x half> @llvm.maximumnum.v8f16(<8 x half> poison, <8 x half> poison)
+ call <16 x half> @llvm.maximumnum.v16f16(<16 x half> poison, <16 x half> poison)
+ ret void
+}
+
+define void @maximumnum_bf16() {
+; CHECK-LABEL: 'maximumnum_bf16'
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:3 Lat:4 SizeLat:4 for: %1 = call <2 x bfloat> @llvm.maximumnum.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:7 Lat:10 SizeLat:10 for: %2 = call <4 x bfloat> @llvm.maximumnum.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of RThru:22 CodeSize:15 Lat:22 SizeLat:22 for: %3 = call <8 x bfloat> @llvm.maximumnum.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of RThru:44 CodeSize:30 Lat:44 SizeLat:44 for: %4 = call <16 x bfloat> @llvm.maximumnum.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ call <2 x bfloat> @llvm.maximumnum.v2fb16(<2 x bfloat> poison, <2 x bfloat> poison)
+ call <4 x bfloat> @llvm.maximumnum.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison)
+ call <8 x bfloat> @llvm.maximumnum.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison)
+ call <16 x bfloat> @llvm.maximumnum.v6bf16(<16 x bfloat> poison, <16 x bfloat> poison)
+ ret void
+}
+
declare i8 @llvm.umin.i8(i8, i8)
declare i16 @llvm.umin.i16(i16, i16)
declare i32 @llvm.umin.i32(i32, i32)
@@ -572,20 +640,3 @@ declare <4 x float> @llvm.maximum.v4f32(<4 x float>, <4 x float>)
declare <8 x float> @llvm.maximum.v8f32(<8 x float>, <8 x float>)
declare <2 x double> @llvm.maximum.v2f64(<2 x double>, <2 x double>)
declare <4 x double> @llvm.maximum.v4f64(<4 x double>, <4 x double>)
-
-declare <2 x half> @llvm.minimumnum.v2f16(<2 x half>, <2 x half>)
-declare <4 x half> @llvm.minimumnum.v4f16(<4 x half>, <4 x half>)
-declare <8 x half> @llvm.minimumnum.v8f16(<8 x half>, <8 x half>)
-declare <16 x half> @llvm.minimumnum.v16f16(<16 x half>, <16 x half>)
-declare <2 x bfloat> @llvm.minimumnum.2bf16(<2 x bfloat>, <2 x bfloat>)
-declare <4 x bfloat> @llvm.minimumnum.4bf16(<4 x bfloat>, <4 x bfloat>)
-declare <8 x bfloat> @llvm.minimumnum.v8bf16(<8 x bfloat>, <8 x bfloat>)
-declare <16 x bfloat> @llvm.minimumnum.v16bf16(<16 x bfloat>, <16 x bfloat>)
-declare <2 x float> @llvm.minimumnum.v2f32(<2 x float>, <2 x float>)
-declare <4 x float> @llvm.minimumnum.v4f32(<4 x float>, <4 x float>)
-declare <8 x float> @llvm.minimumnum.v8f32(<8 x float>, <8 x float>)
-declare <16 x float> @llvm.minimumnum.v16f32(<16 x float>, <16 x float>)
-declare <2 x double> @llvm.minimumnum.v2f64(<2 x double>, <2 x double>)
-declare <4 x double> @llvm.minimumnum.v4f64(<4 x double>, <4 x double>)
-declare <8 x double> @llvm.minimumnum.nxv8f64(<8 x double>, <8 x double>)
-declare <16 x double> @llvm.minimumnum.nxv16f64(<16 x double>, <16 x double>)
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll b/llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll
index 73574dd61d75c..5d1113388015b 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll
@@ -266,6 +266,15 @@ define void @minimumnum() {
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %7 = call <vscale x 8 x double> @llvm.minimumnum.nxv8f64(<vscale x 8 x double> poison, <vscale x 8 x double> poison)
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %8 = call <vscale x 16 x double> @llvm.minimumnum.nxv16f64(<vscale x 16 x double> poison, <vscale x 16 x double> poison)
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %10 = call <vscale x 2 x half> @llvm.minimumnum.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %11 = call <vscale x 4 x half> @llvm.minimumnum.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %12 = call <vscale x 8 x half> @llvm.minimumnum.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %13 = call <vscale x 16 x half> @llvm.minimumnum.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %14 = call <vscale x 2 x bfloat> @llvm.minimumnum.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %15 = call <vscale x 4 x bfloat> @llvm.minimumnum.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %16 = call <vscale x 8 x bfloat> @llvm.minimumnum.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %17 = call <vscale x 16 x bfloat> @llvm.minimumnum.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
call <vscale x 2 x float> @llvm.minimumnum(<vscale x 2 x float> poison, <vscale x 2 x float> poison)
call <vscale x 4 x float> @llvm.minimumnum(<vscale x 4 x float> poison, <vscale x 4 x float> poison)
@@ -276,35 +285,55 @@ define void @minimumnum() {
call <vscale x 8 x double> @llvm.minimumnum(<vscale x 8 x double> poison, <vscale x 8 x double> poison)
call <vscale x 16 x double> @llvm.minimumnum(<vscale x 16 x double> poison, <vscale x 16 x double> poison)
ret void
-}
-
-define void @minimumnum_fp16() {
-; CHECK-LABEL: 'minimumnum_fp16'
-; CHECK-NEXT: Cost Model: Found costs of Invalid for: %1 = call <vscale x 2 x half> @llvm.minimumnum.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison)
-; CHECK-NEXT: Cost Model: Found costs of Invalid for: %2 = call <vscale x 4 x half> @llvm.minimumnum.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison)
-; CHECK-NEXT: Cost Model: Found costs of Invalid for: %3 = call <vscale x 8 x half> @llvm.minimumnum.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison)
-; CHECK-NEXT: Cost Model: Found costs of Invalid for: %4 = call <vscale x 16 x half> @llvm.minimumnum.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison)
-; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
-;
call <vscale x 2 x half> @llvm.minimumnum(<vscale x 2 x half> poison, <vscale x 2 x half> poison)
call <vscale x 4 x half> @llvm.minimumnum(<vscale x 4 x half> poison, <vscale x 4 x half> poison)
call <vscale x 8 x half> @llvm.minimumnum(<vscale x 8 x half> poison, <vscale x 8 x half> poison)
call <vscale x 16 x half> @llvm.minimumnum(<vscale x 16 x half> poison, <vscale x 16 x half> poison)
+ call <vscale x 2 x bfloat> @llvm.minimumnum(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison)
+ call <vscale x 4 x bfloat> @llvm.minimumnum(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison)
+ call <vscale x 8 x bfloat> @llvm.minimumnum(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison)
+ call <vscale x 16 x bfloat> @llvm.minimumnum(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison)
ret void
}
-define void @minimumnum_bf16() {
-; CHECK-LABEL: 'minimumnum_bf16'
-; CHECK-NEXT: Cost Model: Found costs of Invalid for: %1 = call <vscale x 2 x bfloat> @llvm.minimumnum.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison)
-; CHECK-NEXT: Cost Model: Found costs of Invalid for: %2 = call <vscale x 4 x bfloat> @llvm.minimumnum.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison)
-; CHECK-NEXT: Cost Model: Found costs of Invalid for: %3 = call <vscale x 8 x bfloat> @llvm.minimumnum.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison)
-; CHECK-NEXT: Cost Model: Found costs of Invalid for: %4 = call <vscale x 16 x bfloat> @llvm.minimumnum.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison)
+define void @maximumnum() {
+; CHECK-LABEL: 'maximumnum'
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %1 = call <vscale x 2 x float> @llvm.maximumnum.nxv2f32(<vscale x 2 x float> poison, <vscale x 2 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %2 = call <vscale x 4 x float> @llvm.maximumnum.nxv4f32(<vscale x 4 x float> poison, <vscale x 4 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %3 = call <vscale x 8 x float> @llvm.maximumnum.nxv8f32(<vscale x 8 x float> poison, <vscale x 8 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %4 = call <vscale x 16 x float> @llvm.maximumnum.nxv16f32(<vscale x 16 x float> poison, <vscale x 16 x float> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %5 = call <vscale x 2 x double> @llvm.maximumnum.nxv2f64(<vscale x 2 x double> poison, <vscale x 2 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %6 = call <vscale x 4 x double> @llvm.maximumnum.nxv4f64(<vscale x 4 x double> poison, <vscale x 4 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %7 = call <vscale x 8 x double> @llvm.maximumnum.nxv8f64(<vscale x 8 x double> poison, <vscale x 8 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %8 = call <vscale x 16 x double> @llvm.maximumnum.nxv16f64(<vscale x 16 x double> poison, <vscale x 16 x double> poison)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %10 = call <vscale x 2 x half> @llvm.maximumnum.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %11 = call <vscale x 4 x half> @llvm.maximumnum.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %12 = call <vscale x 8 x half> @llvm.maximumnum.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %13 = call <vscale x 16 x half> @llvm.maximumnum.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %14 = call <vscale x 2 x bfloat> @llvm.maximumnum.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %15 = call <vscale x 4 x bfloat> @llvm.maximumnum.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %16 = call <vscale x 8 x bfloat> @llvm.maximumnum.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison)
+; CHECK-NEXT: Cost Model: Found costs of Invalid for: %17 = call <vscale x 16 x bfloat> @llvm.maximumnum.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison)
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
- call <vscale x 2 x bfloat> @llvm.minimumnum(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison)
- call <vscale x 4 x bfloat> @llvm.minimumnum(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison)
- call <vscale x 8 x bfloat> @llvm.minimumnum(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison)
- call <vscale x 16 x bfloat> @llvm.minimumnum(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison)
+ call <vscale x 2 x float> @llvm.maximumnum(<vscale x 2 x float> poison, <vscale x 2 x float> poison)
+ call <vscale x 4 x float> @llvm.maximumnum(<vscale x 4 x float> poison, <vscale x 4 x float> poison)
+ call <vscale x 8 x float> @llvm.maximumnum(<vscale x 8 x float> poison, <vscale x 8 x float> poison)
+ call <vscale x 16 x float> @llvm.maximumnum(<vscale x 16 x float> poison, <vscale x 16 x float> poison)
+ call <vscale x 2 x double> @llvm.maximumnum(<vscale x 2 x double> poison, <vscale x 2 x double> poison)
+ call <vscale x 4 x double> @llvm.maximumnum(<vscale x 4 x double> poison, <vscale x 4 x double> poison)
+ call <vscale x 8 x double> @llvm.maximumnum(<vscale x 8 x double> poison, <vscale x 8 x double> poison)
+ call <vscale x 16 x double> @llvm.maximumnum(<vscale x 16 x double> poison, <vscale x 16 x double> poison)
+ ret void
+ call <vscale x 2 x half> @llvm.maximumnum(<vscale x 2 x half> poison, <vscale x 2 x half> poison)
+ call <vscale x 4 x half> @llvm.maximumnum(<vscale x 4 x half> poison, <vscale x 4 x half> poison)
+ call <vscale x 8 x half> @llvm.maximumnum(<vscale x 8 x half> poison, <vscale x 8 x half> poison)
+ call <vscale x 16 x half> @llvm.maximumnum(<vscale x 16 x half> poison, <vscale x 16 x half> poison)
+ call <vscale x 2 x bfloat> @llvm.maximumnum(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison)
+ call <vscale x 4 x bfloat> @llvm.maximumnum(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison)
+ call <vscale x 8 x bfloat> @llvm.maximumnum(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison)
+ call <vscale x 16 x bfloat> @llvm.maximumnum(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison)
ret void
}
@@ -408,20 +437,3 @@ declare <vscale x 4 x float> @llvm.maximum.nxv4f32(<vscale x 4 x float>, <vscale
declare <vscale x 8 x float> @llvm.maximum.nxv8f32(<vscale x 8 x float>, <vscale x 8 x float>)
declare <vscale x 2 x double> @llvm.maximum.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 4 x double> @llvm.maximum.nxv4f64(<vscale x 4 x double>, <vscale x 4 x double>)
-
-declare <vscale x 2 x half> @llvm.minimumnum.nxv2f16(<vscale x 2 x half>, <vscale x 2 x half>)
-declare <vscale x 4 x half> @llvm.minimumnum.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>)
-declare <vscale x 8 x half> @llvm.minimumnum.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
-declare <vscale x 16 x half> @llvm.minimumnum.nxv16f16(<vscale x 16 x half>, <vscale x 16 x half>)
-declare <vscale x 2 x bfloat> @llvm.minimumnum.nxv2bf16(<vscale x 2 x bfloat>, <vscale x 2 x bfloat>)
-declare <vscale x 4 x bfloat> @llvm.minimumnum.nxv4bf16(<vscale x 4 x bfloat>, <vscale x 4 x bfloat>)
-declare <vscale x 8 x bfloat> @llvm.minimumnum.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
-declare <vscale x 16 x bfloat> @llvm.minimumnum.nxv16bf16(<vscale x 16 x bfloat>, <vscale x 16 x bfloat>)
-declare <vscale x 2 x float> @llvm.minimumnum.nxv2f32(<vscale x 2 x float>, <vscale x 2 x float>)
-declare <vscale x 4 x float> @llvm.minimumnum.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
-declare <vscale x 8 x float> @llvm.minimumnum.nxv8f32(<vscale x 8 x float>, <vscale x 8 x float>)
-declare <vscale x 16 x float> @llvm.minimumnum.nxv16f32(<vscale x 16 x float>, <vscale x 16 x float>)
-declare <vscale x 2 x double> @llvm.minimumnum.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
-declare <vscale x 4 x double> @llvm.minimumnum.nxv4f64(<vscale x 4 x double>, <vscale x 4 x double>)
-declare <vscale x 8 x double> @llvm.minimumnum.nxv8f64(<vscale x 8 x double>, <vscale x 8 x double>)
-declare <vscale x 16 x double> @llvm.minimumnum.nxv16f64(<vscale x 16 x double>, <vscale x 16 x double>)
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/pr151664-cost-hoisted-vector-scalable.ll b/llvm/test/Transforms/LoopVectorize/AArch64/pr151664-cost-hoisted-vector-scalable.ll
index 2823712c9143a..5785a5e3dd6a0 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/pr151664-cost-hoisted-vector-scalable.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/pr151664-cost-hoisted-vector-scalable.ll
@@ -7,10 +7,10 @@
; and hence should not be produced by LoopVectorize. Unfortunately, what is
; actually costed is `<4 x float> @llvm.minimumnum`.
-; CHECK: LV: Found an estimated cost of 3 for VF 1 For instruction: %res = tail call float @llvm.minimumnum.f32(float 0.000000e+00, float 0.000000e+00)
-define void @cost_hoisted_vector_code(ptr %p) {
+; CHECK: LV: Found an estimated cost of 3 for VF 1 For instruction: %res = tail call float @llvm.minimumnum.f32(float %arg, float 0.000000e+00)
+define void @cost_hoisted_vector_code(ptr %p, float %arg) {
; CHECK-LABEL: define void @cost_hoisted_vector_code(
-; CHECK-SAME: ptr [[P:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-SAME: ptr [[P:%.*]], float [[ARG:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul nuw i64 [[TMP0]], 8
@@ -22,8 +22,10 @@ define void @cost_hoisted_vector_code(ptr %p) {
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 -1, [[N_MOD_VF]]
; CHECK-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 8
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[ARG]], i64 0
+; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x float> [[BROADCAST_SPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP6:%.*]] = add i64 1, [[N_VEC]]
-; CHECK-NEXT: [[TMP7:%.*]] = call <vscale x 4 x float> @llvm.minimumnum.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer)
+; CHECK-NEXT: [[TMP7:%.*]] = call <vscale x 4 x float> @llvm.minimumnum.nxv4f32(<vscale x 4 x float> [[BROADCAST_SPLAT]], <vscale x 4 x float> zeroinitializer)
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
@@ -47,7 +49,7 @@ entry:
loop: ; preds = %loop, %entry
%iv = phi i64 [ 1, %entry ], [ %iv.next, %loop ]
%idx = phi i64 [ 0, %entry ], [ %idx.next, %loop ]
- %res = tail call float @llvm.minimumnum.f32(float 0.0, float 0.0)
+ %res = tail call float @llvm.minimumnum.f32(float %arg, float 0.0)
%gep.p.red = getelementptr float, ptr %p, i64 %idx
store float %res, ptr %gep.p.red, align 4
%idx.next = add i64 %idx, 1
More information about the llvm-commits
mailing list