https://github.com/arsenm updated https://github.com/llvm/llvm-project/pull/100522
>From df2b6b7c749629f0ea50f7772329b48ba9450f2f Mon Sep 17 00:00:00 2001 From: Matt Arsenault <matthew.arsena...@amd.com> Date: Thu, 25 Jul 2024 10:47:03 +0400 Subject: [PATCH] AMDGPU: Add baseline test for cost of abs intrinsics --- llvm/test/Analysis/CostModel/AMDGPU/abs.ll | 310 +++++++++++++++++++++ 1 file changed, 310 insertions(+) create mode 100644 llvm/test/Analysis/CostModel/AMDGPU/abs.ll diff --git a/llvm/test/Analysis/CostModel/AMDGPU/abs.ll b/llvm/test/Analysis/CostModel/AMDGPU/abs.ll new file mode 100644 index 0000000000000..f65615b07abc0 --- /dev/null +++ b/llvm/test/Analysis/CostModel/AMDGPU/abs.ll @@ -0,0 +1,310 @@ +; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py +; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=FAST %s +; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=FAST %s +; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=FAST %s +; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=SLOW %s +; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=FAST-SIZE %s +; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=FAST-SIZE %s +; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=FAST-SIZE %s +; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=SLOW-SIZE %s +; END. + +define void @abs_nonpoison() { +; FAST-LABEL: 'abs_nonpoison' +; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 114 for instruction: %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 174 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 198 for instruction: %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 322 for instruction: %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 false) +; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void +; +; SLOW-LABEL: 'abs_nonpoison' +; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 102 for instruction: %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 162 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 198 for instruction: %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 322 for instruction: %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 false) +; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void +; +; FAST-SIZE-LABEL: 'abs_nonpoison' +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 false) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void +; +; SLOW-SIZE-LABEL: 'abs_nonpoison' +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 false) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void +; + %I64 = call i64 @llvm.abs.i64(i64 undef, i1 false) + %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false) + %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false) + %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 false) + %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false) + + %I32 = call i32 @llvm.abs.i32(i32 undef, i1 false) + %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 false) + %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 false) + %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 false) + %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 false) + %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 false) + + %I16 = call i16 @llvm.abs.i16(i16 undef, i1 false) + %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 false) + %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 false) + %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 false) + %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 false) + %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 false) + %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 false) + + %I8 = call i8 @llvm.abs.i8(i8 undef, i1 false) + %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false) + %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false) + %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false) + %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false) + %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 false) + %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 false) + %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 false) + + ret void +} + +define void @abs_poison() { +; FAST-LABEL: 'abs_poison' +; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 114 for instruction: %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 174 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 198 for instruction: %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 322 for instruction: %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 true) +; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void +; +; SLOW-LABEL: 'abs_poison' +; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 102 for instruction: %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 162 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 198 for instruction: %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 322 for instruction: %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 true) +; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void +; +; FAST-SIZE-LABEL: 'abs_poison' +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 true) +; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void +; +; SLOW-SIZE-LABEL: 'abs_poison' +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 true) +; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void +; + %I64 = call i64 @llvm.abs.i64(i64 undef, i1 true) + %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 true) + %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 true) + %V5I64 = call <5 x i64> @llvm.abs.v5i64(<5 x i64> undef, i1 true) + %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 true) + + %I32 = call i32 @llvm.abs.i32(i32 undef, i1 true) + %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 true) + %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 true) + %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 true) + %V9I32 = call <9 x i32> @llvm.abs.v9i32(<9 x i32> undef, i1 true) + %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 true) + + %I16 = call i16 @llvm.abs.i16(i16 undef, i1 true) + %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 true) + %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 true) + %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 true) + %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 true) + %V17I16 = call <17 x i16> @llvm.abs.v17i16(<17 x i16> undef, i1 true) + %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 true) + + %I8 = call i8 @llvm.abs.i8(i8 undef, i1 true) + %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 true) + %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 true) + %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 true) + %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 true) + %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 true) + %V33I8 = call <33 x i8> @llvm.abs.v33i8(<33 x i8> undef, i1 true) + %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 true) + + ret void +} _______________________________________________ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits