diff options
Diffstat (limited to 'llvm/test/Analysis/CostModel/X86/reduce-add.ll')
| -rw-r--r-- | llvm/test/Analysis/CostModel/X86/reduce-add.ll | 37 |
1 files changed, 37 insertions, 0 deletions
diff --git a/llvm/test/Analysis/CostModel/X86/reduce-add.ll b/llvm/test/Analysis/CostModel/X86/reduce-add.ll index 090813a597b..2efadd801b0 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-add.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-add.ll @@ -8,6 +8,8 @@ ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BW ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512DQ +; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mcpu=slm | FileCheck %s --check-prefixes=SLM + define i32 @reduce_i64(i32 %arg) { ; SSE-LABEL: 'reduce_i64' ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.v1i64(<1 x i64> undef) @@ -33,6 +35,14 @@ define i32 @reduce_i64(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.v16i64(<16 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; +; SLM-LABEL: 'reduce_i64' +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.v1i64(<1 x i64> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.v2i64(<2 x i64> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.v4i64(<4 x i64> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.v8i64(<8 x i64> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.v16i64(<16 x i64> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef +; %V1 = call i64 @llvm.experimental.vector.reduce.add.v1i64(<1 x i64> undef) %V2 = call i64 @llvm.experimental.vector.reduce.add.v2i64(<2 x i64> undef) %V4 = call i64 @llvm.experimental.vector.reduce.add.v4i64(<4 x i64> undef) @@ -66,6 +76,14 @@ define i32 @reduce_i32(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.v32i32(<32 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; +; SLM-LABEL: 'reduce_i32' +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.v2i32(<2 x i32> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.v8i32(<8 x i32> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.v16i32(<16 x i32> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.v32i32(<32 x i32> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef +; %V2 = call i32 @llvm.experimental.vector.reduce.add.v2i32(<2 x i32> undef) %V4 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> undef) %V8 = call i32 @llvm.experimental.vector.reduce.add.v8i32(<8 x i32> undef) @@ -120,6 +138,15 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.v64i16(<64 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; +; SLM-LABEL: 'reduce_i16' +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.v2i16(<2 x i16> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.v4i16(<4 x i16> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.v16i16(<16 x i16> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.v32i16(<32 x i16> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.v64i16(<64 x i16> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef +; %V2 = call i16 @llvm.experimental.vector.reduce.add.v2i16(<2 x i16> undef) %V4 = call i16 @llvm.experimental.vector.reduce.add.v4i16(<4 x i16> undef) %V8 = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> undef) @@ -180,6 +207,16 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.v128i8(<128 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; +; SLM-LABEL: 'reduce_i8' +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.v32i8(<32 x i8> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.v64i8(<64 x i8> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.v128i8(<128 x i8> undef) +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef +; %V2 = call i8 @llvm.experimental.vector.reduce.add.v2i8(<2 x i8> undef) %V4 = call i8 @llvm.experimental.vector.reduce.add.v4i8(<4 x i8> undef) %V8 = call i8 @llvm.experimental.vector.reduce.add.v8i8(<8 x i8> undef) |
