[llvm] 53f738c - [RISCV] Add empirical costs for integer min/max and saturing add/sub
Philip Reames via llvm-commits
llvm-commits at lists.llvm.org
Thu Aug 25 09:27:29 PDT 2022
Author: Philip Reames
Date: 2022-08-25T09:27:17-07:00
New Revision: 53f738ce7e6cc22d58c6cc1042c7b49cd81f75ae
URL: https://github.com/llvm/llvm-project/commit/53f738ce7e6cc22d58c6cc1042c7b49cd81f75ae
DIFF: https://github.com/llvm/llvm-project/commit/53f738ce7e6cc22d58c6cc1042c7b49cd81f75ae.diff
LOG: [RISCV] Add empirical costs for integer min/max and saturing add/sub
All of these are lowered to a single instruction for all legal vector types.
Added:
Modified:
llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
llvm/test/Analysis/CostModel/RISCV/int-min-max.ll
llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 718f95127300..4593b0678618 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -438,6 +438,254 @@ static const CostTblEntry VectorIntrinsicCostTable[]{
{Intrinsic::ctpop, MVT::nxv2i64, 21},
{Intrinsic::ctpop, MVT::nxv4i64, 21},
{Intrinsic::ctpop, MVT::nxv8i64, 21},
+ {Intrinsic::smax, MVT::v2i8, 1},
+ {Intrinsic::smax, MVT::v4i8, 1},
+ {Intrinsic::smax, MVT::v8i8, 1},
+ {Intrinsic::smax, MVT::v16i8, 1},
+ {Intrinsic::smax, MVT::nxv2i8, 1},
+ {Intrinsic::smax, MVT::nxv4i8, 1},
+ {Intrinsic::smax, MVT::nxv8i8, 1},
+ {Intrinsic::smax, MVT::nxv16i8, 1},
+ {Intrinsic::smax, MVT::v2i16, 1},
+ {Intrinsic::smax, MVT::v4i16, 1},
+ {Intrinsic::smax, MVT::v8i16, 1},
+ {Intrinsic::smax, MVT::v16i16, 1},
+ {Intrinsic::smax, MVT::nxv2i16, 1},
+ {Intrinsic::smax, MVT::nxv4i16, 1},
+ {Intrinsic::smax, MVT::nxv8i16, 1},
+ {Intrinsic::smax, MVT::nxv16i16, 1},
+ {Intrinsic::smax, MVT::v2i32, 1},
+ {Intrinsic::smax, MVT::v4i32, 1},
+ {Intrinsic::smax, MVT::v8i32, 1},
+ {Intrinsic::smax, MVT::v16i32, 1},
+ {Intrinsic::smax, MVT::nxv2i32, 1},
+ {Intrinsic::smax, MVT::nxv4i32, 1},
+ {Intrinsic::smax, MVT::nxv8i32, 1},
+ {Intrinsic::smax, MVT::nxv16i32, 1},
+ {Intrinsic::smax, MVT::v2i64, 1},
+ {Intrinsic::smax, MVT::v4i64, 1},
+ {Intrinsic::smax, MVT::v8i64, 1},
+ {Intrinsic::smax, MVT::v16i64, 1},
+ {Intrinsic::smax, MVT::nxv2i64, 1},
+ {Intrinsic::smax, MVT::nxv4i64, 1},
+ {Intrinsic::smax, MVT::nxv8i64, 1},
+ {Intrinsic::smin, MVT::v2i8, 1},
+ {Intrinsic::smin, MVT::v4i8, 1},
+ {Intrinsic::smin, MVT::v8i8, 1},
+ {Intrinsic::smin, MVT::v16i8, 1},
+ {Intrinsic::smin, MVT::nxv2i8, 1},
+ {Intrinsic::smin, MVT::nxv4i8, 1},
+ {Intrinsic::smin, MVT::nxv8i8, 1},
+ {Intrinsic::smin, MVT::nxv16i8, 1},
+ {Intrinsic::smin, MVT::v2i16, 1},
+ {Intrinsic::smin, MVT::v4i16, 1},
+ {Intrinsic::smin, MVT::v8i16, 1},
+ {Intrinsic::smin, MVT::v16i16, 1},
+ {Intrinsic::smin, MVT::nxv2i16, 1},
+ {Intrinsic::smin, MVT::nxv4i16, 1},
+ {Intrinsic::smin, MVT::nxv8i16, 1},
+ {Intrinsic::smin, MVT::nxv16i16, 1},
+ {Intrinsic::smin, MVT::v2i32, 1},
+ {Intrinsic::smin, MVT::v4i32, 1},
+ {Intrinsic::smin, MVT::v8i32, 1},
+ {Intrinsic::smin, MVT::v16i32, 1},
+ {Intrinsic::smin, MVT::nxv2i32, 1},
+ {Intrinsic::smin, MVT::nxv4i32, 1},
+ {Intrinsic::smin, MVT::nxv8i32, 1},
+ {Intrinsic::smin, MVT::nxv16i32, 1},
+ {Intrinsic::smin, MVT::v2i64, 1},
+ {Intrinsic::smin, MVT::v4i64, 1},
+ {Intrinsic::smin, MVT::v8i64, 1},
+ {Intrinsic::smin, MVT::v16i64, 1},
+ {Intrinsic::smin, MVT::nxv2i64, 1},
+ {Intrinsic::smin, MVT::nxv4i64, 1},
+ {Intrinsic::smin, MVT::nxv8i64, 1},
+ {Intrinsic::umax, MVT::v2i8, 1},
+ {Intrinsic::umax, MVT::v4i8, 1},
+ {Intrinsic::umax, MVT::v8i8, 1},
+ {Intrinsic::umax, MVT::v16i8, 1},
+ {Intrinsic::umax, MVT::nxv2i8, 1},
+ {Intrinsic::umax, MVT::nxv4i8, 1},
+ {Intrinsic::umax, MVT::nxv8i8, 1},
+ {Intrinsic::umax, MVT::nxv16i8, 1},
+ {Intrinsic::umax, MVT::v2i16, 1},
+ {Intrinsic::umax, MVT::v4i16, 1},
+ {Intrinsic::umax, MVT::v8i16, 1},
+ {Intrinsic::umax, MVT::v16i16, 1},
+ {Intrinsic::umax, MVT::nxv2i16, 1},
+ {Intrinsic::umax, MVT::nxv4i16, 1},
+ {Intrinsic::umax, MVT::nxv8i16, 1},
+ {Intrinsic::umax, MVT::nxv16i16, 1},
+ {Intrinsic::umax, MVT::v2i32, 1},
+ {Intrinsic::umax, MVT::v4i32, 1},
+ {Intrinsic::umax, MVT::v8i32, 1},
+ {Intrinsic::umax, MVT::v16i32, 1},
+ {Intrinsic::umax, MVT::nxv2i32, 1},
+ {Intrinsic::umax, MVT::nxv4i32, 1},
+ {Intrinsic::umax, MVT::nxv8i32, 1},
+ {Intrinsic::umax, MVT::nxv16i32, 1},
+ {Intrinsic::umax, MVT::v2i64, 1},
+ {Intrinsic::umax, MVT::v4i64, 1},
+ {Intrinsic::umax, MVT::v8i64, 1},
+ {Intrinsic::umax, MVT::v16i64, 1},
+ {Intrinsic::umax, MVT::nxv2i64, 1},
+ {Intrinsic::umax, MVT::nxv4i64, 1},
+ {Intrinsic::umax, MVT::nxv8i64, 1},
+ {Intrinsic::umin, MVT::v2i8, 1},
+ {Intrinsic::umin, MVT::v4i8, 1},
+ {Intrinsic::umin, MVT::v8i8, 1},
+ {Intrinsic::umin, MVT::v16i8, 1},
+ {Intrinsic::umin, MVT::nxv2i8, 1},
+ {Intrinsic::umin, MVT::nxv4i8, 1},
+ {Intrinsic::umin, MVT::nxv8i8, 1},
+ {Intrinsic::umin, MVT::nxv16i8, 1},
+ {Intrinsic::umin, MVT::v2i16, 1},
+ {Intrinsic::umin, MVT::v4i16, 1},
+ {Intrinsic::umin, MVT::v8i16, 1},
+ {Intrinsic::umin, MVT::v16i16, 1},
+ {Intrinsic::umin, MVT::nxv2i16, 1},
+ {Intrinsic::umin, MVT::nxv4i16, 1},
+ {Intrinsic::umin, MVT::nxv8i16, 1},
+ {Intrinsic::umin, MVT::nxv16i16, 1},
+ {Intrinsic::umin, MVT::v2i32, 1},
+ {Intrinsic::umin, MVT::v4i32, 1},
+ {Intrinsic::umin, MVT::v8i32, 1},
+ {Intrinsic::umin, MVT::v16i32, 1},
+ {Intrinsic::umin, MVT::nxv2i32, 1},
+ {Intrinsic::umin, MVT::nxv4i32, 1},
+ {Intrinsic::umin, MVT::nxv8i32, 1},
+ {Intrinsic::umin, MVT::nxv16i32, 1},
+ {Intrinsic::umin, MVT::v2i64, 1},
+ {Intrinsic::umin, MVT::v4i64, 1},
+ {Intrinsic::umin, MVT::v8i64, 1},
+ {Intrinsic::umin, MVT::v16i64, 1},
+ {Intrinsic::umin, MVT::nxv2i64, 1},
+ {Intrinsic::umin, MVT::nxv4i64, 1},
+ {Intrinsic::umin, MVT::nxv8i64, 1},
+ {Intrinsic::sadd_sat, MVT::v2i8, 1},
+ {Intrinsic::sadd_sat, MVT::v4i8, 1},
+ {Intrinsic::sadd_sat, MVT::v8i8, 1},
+ {Intrinsic::sadd_sat, MVT::v16i8, 1},
+ {Intrinsic::sadd_sat, MVT::nxv2i8, 1},
+ {Intrinsic::sadd_sat, MVT::nxv4i8, 1},
+ {Intrinsic::sadd_sat, MVT::nxv8i8, 1},
+ {Intrinsic::sadd_sat, MVT::nxv16i8, 1},
+ {Intrinsic::sadd_sat, MVT::v2i16, 1},
+ {Intrinsic::sadd_sat, MVT::v4i16, 1},
+ {Intrinsic::sadd_sat, MVT::v8i16, 1},
+ {Intrinsic::sadd_sat, MVT::v16i16, 1},
+ {Intrinsic::sadd_sat, MVT::nxv2i16, 1},
+ {Intrinsic::sadd_sat, MVT::nxv4i16, 1},
+ {Intrinsic::sadd_sat, MVT::nxv8i16, 1},
+ {Intrinsic::sadd_sat, MVT::nxv16i16, 1},
+ {Intrinsic::sadd_sat, MVT::v2i32, 1},
+ {Intrinsic::sadd_sat, MVT::v4i32, 1},
+ {Intrinsic::sadd_sat, MVT::v8i32, 1},
+ {Intrinsic::sadd_sat, MVT::v16i32, 1},
+ {Intrinsic::sadd_sat, MVT::nxv2i32, 1},
+ {Intrinsic::sadd_sat, MVT::nxv4i32, 1},
+ {Intrinsic::sadd_sat, MVT::nxv8i32, 1},
+ {Intrinsic::sadd_sat, MVT::nxv16i32, 1},
+ {Intrinsic::sadd_sat, MVT::v2i64, 1},
+ {Intrinsic::sadd_sat, MVT::v4i64, 1},
+ {Intrinsic::sadd_sat, MVT::v8i64, 1},
+ {Intrinsic::sadd_sat, MVT::v16i64, 1},
+ {Intrinsic::sadd_sat, MVT::nxv2i64, 1},
+ {Intrinsic::sadd_sat, MVT::nxv4i64, 1},
+ {Intrinsic::sadd_sat, MVT::nxv8i64, 1},
+ {Intrinsic::uadd_sat, MVT::v2i8, 1},
+ {Intrinsic::uadd_sat, MVT::v4i8, 1},
+ {Intrinsic::uadd_sat, MVT::v8i8, 1},
+ {Intrinsic::uadd_sat, MVT::v16i8, 1},
+ {Intrinsic::uadd_sat, MVT::nxv2i8, 1},
+ {Intrinsic::uadd_sat, MVT::nxv4i8, 1},
+ {Intrinsic::uadd_sat, MVT::nxv8i8, 1},
+ {Intrinsic::uadd_sat, MVT::nxv16i8, 1},
+ {Intrinsic::uadd_sat, MVT::v2i16, 1},
+ {Intrinsic::uadd_sat, MVT::v4i16, 1},
+ {Intrinsic::uadd_sat, MVT::v8i16, 1},
+ {Intrinsic::uadd_sat, MVT::v16i16, 1},
+ {Intrinsic::uadd_sat, MVT::nxv2i16, 1},
+ {Intrinsic::uadd_sat, MVT::nxv4i16, 1},
+ {Intrinsic::uadd_sat, MVT::nxv8i16, 1},
+ {Intrinsic::uadd_sat, MVT::nxv16i16, 1},
+ {Intrinsic::uadd_sat, MVT::v2i32, 1},
+ {Intrinsic::uadd_sat, MVT::v4i32, 1},
+ {Intrinsic::uadd_sat, MVT::v8i32, 1},
+ {Intrinsic::uadd_sat, MVT::v16i32, 1},
+ {Intrinsic::uadd_sat, MVT::nxv2i32, 1},
+ {Intrinsic::uadd_sat, MVT::nxv4i32, 1},
+ {Intrinsic::uadd_sat, MVT::nxv8i32, 1},
+ {Intrinsic::uadd_sat, MVT::nxv16i32, 1},
+ {Intrinsic::uadd_sat, MVT::v2i64, 1},
+ {Intrinsic::uadd_sat, MVT::v4i64, 1},
+ {Intrinsic::uadd_sat, MVT::v8i64, 1},
+ {Intrinsic::uadd_sat, MVT::v16i64, 1},
+ {Intrinsic::uadd_sat, MVT::nxv2i64, 1},
+ {Intrinsic::uadd_sat, MVT::nxv4i64, 1},
+ {Intrinsic::uadd_sat, MVT::nxv8i64, 1},
+ {Intrinsic::usub_sat, MVT::v2i8, 1},
+ {Intrinsic::usub_sat, MVT::v4i8, 1},
+ {Intrinsic::usub_sat, MVT::v8i8, 1},
+ {Intrinsic::usub_sat, MVT::v16i8, 1},
+ {Intrinsic::usub_sat, MVT::nxv2i8, 1},
+ {Intrinsic::usub_sat, MVT::nxv4i8, 1},
+ {Intrinsic::usub_sat, MVT::nxv8i8, 1},
+ {Intrinsic::usub_sat, MVT::nxv16i8, 1},
+ {Intrinsic::usub_sat, MVT::v2i16, 1},
+ {Intrinsic::usub_sat, MVT::v4i16, 1},
+ {Intrinsic::usub_sat, MVT::v8i16, 1},
+ {Intrinsic::usub_sat, MVT::v16i16, 1},
+ {Intrinsic::usub_sat, MVT::nxv2i16, 1},
+ {Intrinsic::usub_sat, MVT::nxv4i16, 1},
+ {Intrinsic::usub_sat, MVT::nxv8i16, 1},
+ {Intrinsic::usub_sat, MVT::nxv16i16, 1},
+ {Intrinsic::usub_sat, MVT::v2i32, 1},
+ {Intrinsic::usub_sat, MVT::v4i32, 1},
+ {Intrinsic::usub_sat, MVT::v8i32, 1},
+ {Intrinsic::usub_sat, MVT::v16i32, 1},
+ {Intrinsic::usub_sat, MVT::nxv2i32, 1},
+ {Intrinsic::usub_sat, MVT::nxv4i32, 1},
+ {Intrinsic::usub_sat, MVT::nxv8i32, 1},
+ {Intrinsic::usub_sat, MVT::nxv16i32, 1},
+ {Intrinsic::usub_sat, MVT::v2i64, 1},
+ {Intrinsic::usub_sat, MVT::v4i64, 1},
+ {Intrinsic::usub_sat, MVT::v8i64, 1},
+ {Intrinsic::usub_sat, MVT::v16i64, 1},
+ {Intrinsic::usub_sat, MVT::nxv2i64, 1},
+ {Intrinsic::usub_sat, MVT::nxv4i64, 1},
+ {Intrinsic::usub_sat, MVT::nxv8i64, 1},
+ {Intrinsic::ssub_sat, MVT::v2i8, 1},
+ {Intrinsic::ssub_sat, MVT::v4i8, 1},
+ {Intrinsic::ssub_sat, MVT::v8i8, 1},
+ {Intrinsic::ssub_sat, MVT::v16i8, 1},
+ {Intrinsic::ssub_sat, MVT::nxv2i8, 1},
+ {Intrinsic::ssub_sat, MVT::nxv4i8, 1},
+ {Intrinsic::ssub_sat, MVT::nxv8i8, 1},
+ {Intrinsic::ssub_sat, MVT::nxv16i8, 1},
+ {Intrinsic::ssub_sat, MVT::v2i16, 1},
+ {Intrinsic::ssub_sat, MVT::v4i16, 1},
+ {Intrinsic::ssub_sat, MVT::v8i16, 1},
+ {Intrinsic::ssub_sat, MVT::v16i16, 1},
+ {Intrinsic::ssub_sat, MVT::nxv2i16, 1},
+ {Intrinsic::ssub_sat, MVT::nxv4i16, 1},
+ {Intrinsic::ssub_sat, MVT::nxv8i16, 1},
+ {Intrinsic::ssub_sat, MVT::nxv16i16, 1},
+ {Intrinsic::ssub_sat, MVT::v2i32, 1},
+ {Intrinsic::ssub_sat, MVT::v4i32, 1},
+ {Intrinsic::ssub_sat, MVT::v8i32, 1},
+ {Intrinsic::ssub_sat, MVT::v16i32, 1},
+ {Intrinsic::ssub_sat, MVT::nxv2i32, 1},
+ {Intrinsic::ssub_sat, MVT::nxv4i32, 1},
+ {Intrinsic::ssub_sat, MVT::nxv8i32, 1},
+ {Intrinsic::ssub_sat, MVT::nxv16i32, 1},
+ {Intrinsic::ssub_sat, MVT::v2i64, 1},
+ {Intrinsic::ssub_sat, MVT::v4i64, 1},
+ {Intrinsic::ssub_sat, MVT::v8i64, 1},
+ {Intrinsic::ssub_sat, MVT::v16i64, 1},
+ {Intrinsic::ssub_sat, MVT::nxv2i64, 1},
+ {Intrinsic::ssub_sat, MVT::nxv4i64, 1},
+ {Intrinsic::ssub_sat, MVT::nxv8i64, 1},
};
InstructionCost
diff --git a/llvm/test/Analysis/CostModel/RISCV/int-min-max.ll b/llvm/test/Analysis/CostModel/RISCV/int-min-max.ll
index d05e3f0d4cdb..e27cf2252bd1 100644
--- a/llvm/test/Analysis/CostModel/RISCV/int-min-max.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/int-min-max.ll
@@ -1,43 +1,43 @@
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v | FileCheck %s
+; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v -riscv-v-vector-bits-min=-1 | FileCheck %s
define void @smax() {
; CHECK-LABEL: 'smax'
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %2 = call <2 x i8> @llvm.smax.v2i8(<2 x i8> undef, <2 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %3 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %4 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %5 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x i8> @llvm.smax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x i8> @llvm.smax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x i8> @llvm.smax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x i8> @llvm.smax.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.smax.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.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.smax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.smax.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.smax.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.smax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %10 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %11 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %12 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %13 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %14 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <vscale x 2 x i16> @llvm.smax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %16 = call <vscale x 4 x i16> @llvm.smax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 8 x i16> @llvm.smax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %18 = call <vscale x 16 x i16> @llvm.smax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.smax.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.smax.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.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.smax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.smax.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.smax.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.smax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %19 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %20 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %21 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %22 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %23 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %24 = call <vscale x 2 x i32> @llvm.smax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %25 = call <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %26 = call <vscale x 8 x i32> @llvm.smax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %27 = call <vscale x 16 x i32> @llvm.smax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.smax.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.smax.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.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.smax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.smax.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.smax.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.smax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %28 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %29 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %30 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %31 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %32 = call <16 x i64> @llvm.smax.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %33 = call <vscale x 2 x i64> @llvm.smax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %34 = call <vscale x 4 x i64> @llvm.smax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %35 = call <vscale x 8 x i64> @llvm.smax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.smax.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.smax.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.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.smax.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.smax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.smax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.smax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
call i8 @llvm.smax.i8(i8 undef, i8 undef)
@@ -81,40 +81,40 @@ define void @smax() {
define void @smin() {
; CHECK-LABEL: 'smin'
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %2 = call <2 x i8> @llvm.smin.v2i8(<2 x i8> undef, <2 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %3 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %4 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %5 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x i8> @llvm.smin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x i8> @llvm.smin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x i8> @llvm.smin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x i8> @llvm.smin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x i8> @llvm.smin.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.smin.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.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.smin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.smin.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.smin.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.smin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %10 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %11 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %12 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %13 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %14 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <vscale x 2 x i16> @llvm.smin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %16 = call <vscale x 4 x i16> @llvm.smin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 8 x i16> @llvm.smin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %18 = call <vscale x 16 x i16> @llvm.smin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.smin.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.smin.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.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.smin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.smin.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.smin.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.smin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %19 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %20 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %21 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %22 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %23 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %24 = call <vscale x 2 x i32> @llvm.smin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %25 = call <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %26 = call <vscale x 8 x i32> @llvm.smin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %27 = call <vscale x 16 x i32> @llvm.smin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.smin.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.smin.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.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.smin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.smin.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.smin.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.smin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %28 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %29 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %30 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %31 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %32 = call <16 x i64> @llvm.smin.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %33 = call <vscale x 2 x i64> @llvm.smin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %34 = call <vscale x 4 x i64> @llvm.smin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %35 = call <vscale x 8 x i64> @llvm.smin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.smin.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.smin.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.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.smin.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.smin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.smin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.smin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
call i8 @llvm.smin.i8(i8 undef, i8 undef)
@@ -158,40 +158,40 @@ define void @smin() {
define void @umax() {
; CHECK-LABEL: 'umax'
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %2 = call <2 x i8> @llvm.umax.v2i8(<2 x i8> undef, <2 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %3 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %4 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %5 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x i8> @llvm.umax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x i8> @llvm.umax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x i8> @llvm.umax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x i8> @llvm.umax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x i8> @llvm.umax.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.umax.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.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.umax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.umax.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.umax.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.umax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %10 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %11 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %12 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %13 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %14 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <vscale x 2 x i16> @llvm.umax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %16 = call <vscale x 4 x i16> @llvm.umax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 8 x i16> @llvm.umax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %18 = call <vscale x 16 x i16> @llvm.umax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.umax.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.umax.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.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.umax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.umax.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.umax.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.umax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %19 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %20 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %21 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %22 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %23 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %24 = call <vscale x 2 x i32> @llvm.umax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %25 = call <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %26 = call <vscale x 8 x i32> @llvm.umax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %27 = call <vscale x 16 x i32> @llvm.umax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.umax.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.umax.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.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.umax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.umax.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.umax.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.umax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %28 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %29 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %30 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %31 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %32 = call <16 x i64> @llvm.umax.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %33 = call <vscale x 2 x i64> @llvm.umax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %34 = call <vscale x 4 x i64> @llvm.umax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %35 = call <vscale x 8 x i64> @llvm.umax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.umax.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.umax.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.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.umax.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.umax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.umax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.umax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
call i8 @llvm.umax.i8(i8 undef, i8 undef)
@@ -235,40 +235,40 @@ define void @umax() {
define void @umin() {
; CHECK-LABEL: 'umin'
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %2 = call <2 x i8> @llvm.umin.v2i8(<2 x i8> undef, <2 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %3 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %4 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %5 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x i8> @llvm.umin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x i8> @llvm.umin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x i8> @llvm.umin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x i8> @llvm.umin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x i8> @llvm.umin.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.umin.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.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.umin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.umin.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.umin.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.umin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %10 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %11 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %12 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %13 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %14 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <vscale x 2 x i16> @llvm.umin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %16 = call <vscale x 4 x i16> @llvm.umin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 8 x i16> @llvm.umin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %18 = call <vscale x 16 x i16> @llvm.umin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.umin.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.umin.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.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.umin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.umin.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.umin.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.umin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %19 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %20 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %21 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %22 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %23 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %24 = call <vscale x 2 x i32> @llvm.umin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %25 = call <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %26 = call <vscale x 8 x i32> @llvm.umin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %27 = call <vscale x 16 x i32> @llvm.umin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.umin.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.umin.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.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.umin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.umin.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.umin.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.umin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %28 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %29 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %30 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %31 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %32 = call <16 x i64> @llvm.umin.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %33 = call <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %34 = call <vscale x 4 x i64> @llvm.umin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %35 = call <vscale x 8 x i64> @llvm.umin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.umin.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.umin.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.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.umin.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.umin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.umin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
call i8 @llvm.umin.i8(i8 undef, 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 bf886bdf7e87..75b5fd6a490d 100644
--- a/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll
@@ -1,43 +1,43 @@
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v | FileCheck %s
+; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v -riscv-v-vector-bits-min=-1 | FileCheck %s
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 24 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 48 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 96 for instruction: %4 = call <8 x i8> @llvm.sadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %5 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x i8> @llvm.sadd.sat.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 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 7 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 7 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 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)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.sadd.sat.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; 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 24 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 48 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 96 for instruction: %13 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %14 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <vscale x 2 x i16> @llvm.sadd.sat.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 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 7 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 7 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 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)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.sadd.sat.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; 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 24 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 48 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 96 for instruction: %22 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %23 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %24 = call <vscale x 2 x i32> @llvm.sadd.sat.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 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 7 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 7 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 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)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.sadd.sat.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; 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 24 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 48 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 96 for instruction: %31 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %32 = call <16 x i64> @llvm.sadd.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %33 = call <vscale x 2 x i64> @llvm.sadd.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %34 = call <vscale x 4 x i64> @llvm.sadd.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %35 = call <vscale x 8 x i64> @llvm.sadd.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x 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)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.sadd.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.sadd.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.sadd.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.sadd.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
@@ -81,40 +81,40 @@ 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: %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 20 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 40 for instruction: %4 = call <8 x i8> @llvm.uadd.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %5 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %6 = call <vscale x 2 x i8> @llvm.uadd.sat.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 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 3 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 3 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 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)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.uadd.sat.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; 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: %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 20 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 40 for instruction: %13 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %14 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %15 = call <vscale x 2 x i16> @llvm.uadd.sat.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 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 3 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 3 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 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)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.uadd.sat.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; 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: %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 20 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 40 for instruction: %22 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %23 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %24 = call <vscale x 2 x i32> @llvm.uadd.sat.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 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 3 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 3 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 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)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.uadd.sat.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; 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: %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 20 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 40 for instruction: %31 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %32 = call <16 x i64> @llvm.uadd.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %33 = call <vscale x 2 x i64> @llvm.uadd.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %34 = call <vscale x 4 x i64> @llvm.uadd.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %35 = call <vscale x 8 x i64> @llvm.uadd.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x 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)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.uadd.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.uadd.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.uadd.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.uadd.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
@@ -158,40 +158,40 @@ 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: %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 20 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 40 for instruction: %4 = call <8 x i8> @llvm.usub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %5 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %6 = call <vscale x 2 x i8> @llvm.usub.sat.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 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 3 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 3 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 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)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.usub.sat.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; 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: %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 20 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 40 for instruction: %13 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %14 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %15 = call <vscale x 2 x i16> @llvm.usub.sat.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 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 3 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 3 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 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)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.usub.sat.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; 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: %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 20 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 40 for instruction: %22 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %23 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %24 = call <vscale x 2 x i32> @llvm.usub.sat.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 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 3 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 3 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 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)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.usub.sat.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; 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: %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 20 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 40 for instruction: %31 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %32 = call <16 x i64> @llvm.usub.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %33 = call <vscale x 2 x i64> @llvm.usub.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %34 = call <vscale x 4 x i64> @llvm.usub.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %35 = call <vscale x 8 x i64> @llvm.usub.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x 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)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.usub.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.usub.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.usub.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.usub.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
@@ -235,40 +235,40 @@ 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 24 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 48 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 96 for instruction: %4 = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> undef, <8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %5 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x i8> @llvm.ssub.sat.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 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 7 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 7 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 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)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> undef, <16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.ssub.sat.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; 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 24 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 48 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 96 for instruction: %13 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %14 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <vscale x 2 x i16> @llvm.ssub.sat.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 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 7 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 7 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 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)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.ssub.sat.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; 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 24 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 48 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 96 for instruction: %22 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %23 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %24 = call <vscale x 2 x i32> @llvm.ssub.sat.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 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 7 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 7 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 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)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.ssub.sat.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; 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 24 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 48 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 96 for instruction: %31 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %32 = call <16 x i64> @llvm.ssub.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %33 = call <vscale x 2 x i64> @llvm.ssub.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %34 = call <vscale x 4 x i64> @llvm.ssub.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %35 = call <vscale x 8 x i64> @llvm.ssub.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x 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)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.ssub.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.ssub.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.ssub.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.ssub.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
More information about the llvm-commits
mailing list