| ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 5 |
| ; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=hawaii < %s | FileCheck -check-prefixes=ALL,GFX7 %s |
| ; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=tonga < %s | FileCheck -check-prefixes=ALL,GFX8PLUS %s |
| ; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL,GFX8PLUS %s |
| ; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1030 < %s | FileCheck -check-prefixes=ALL,GFX8PLUS %s |
| |
| ; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=hawaii < %s | FileCheck -check-prefixes=ALL-SIZE,GFX7-SIZE %s |
| ; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=tonga < %s | FileCheck -check-prefixes=ALL-SIZE,GFX8PLUS-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=ALL-SIZE,GFX8PLUS-SIZE %s |
| ; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1030 < %s | FileCheck -check-prefixes=ALL-SIZE,GFX8PLUS-SIZE %s |
| |
| define void @ldexp_f16_i32() { |
| ; GFX7-LABEL: 'ldexp_f16_i32' |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.ldexp.f16.i32(half undef, i32 undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2f16 = call <2 x half> @llvm.ldexp.v2f16.v2i32(<2 x half> undef, <2 x i32> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v3f16 = call <3 x half> @llvm.ldexp.v3f16.v3i32(<3 x half> undef, <3 x i32> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v4f16 = call <4 x half> @llvm.ldexp.v4f16.v4i32(<4 x half> undef, <4 x i32> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %v5f16 = call <5 x half> @llvm.ldexp.v5f16.v5i32(<5 x half> undef, <5 x i32> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v8f16 = call <8 x half> @llvm.ldexp.v8f16.v8i32(<8 x half> undef, <8 x i32> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v16f16 = call <16 x half> @llvm.ldexp.v16f16.v16i32(<16 x half> undef, <16 x i32> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %v17f16 = call <17 x half> @llvm.ldexp.v17f16.v17i32(<17 x half> undef, <17 x i32> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void |
| ; |
| ; GFX8PLUS-LABEL: 'ldexp_f16_i32' |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.ldexp.f16.i32(half undef, i32 undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2f16 = call <2 x half> @llvm.ldexp.v2f16.v2i32(<2 x half> undef, <2 x i32> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %v3f16 = call <3 x half> @llvm.ldexp.v3f16.v3i32(<3 x half> undef, <3 x i32> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4f16 = call <4 x half> @llvm.ldexp.v4f16.v4i32(<4 x half> undef, <4 x i32> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %v5f16 = call <5 x half> @llvm.ldexp.v5f16.v5i32(<5 x half> undef, <5 x i32> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8f16 = call <8 x half> @llvm.ldexp.v8f16.v8i32(<8 x half> undef, <8 x i32> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16f16 = call <16 x half> @llvm.ldexp.v16f16.v16i32(<16 x half> undef, <16 x i32> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %v17f16 = call <17 x half> @llvm.ldexp.v17f16.v17i32(<17 x half> undef, <17 x i32> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void |
| ; |
| ; GFX7-SIZE-LABEL: 'ldexp_f16_i32' |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.ldexp.f16.i32(half undef, i32 undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2f16 = call <2 x half> @llvm.ldexp.v2f16.v2i32(<2 x half> undef, <2 x i32> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v3f16 = call <3 x half> @llvm.ldexp.v3f16.v3i32(<3 x half> undef, <3 x i32> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v4f16 = call <4 x half> @llvm.ldexp.v4f16.v4i32(<4 x half> undef, <4 x i32> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %v5f16 = call <5 x half> @llvm.ldexp.v5f16.v5i32(<5 x half> undef, <5 x i32> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v8f16 = call <8 x half> @llvm.ldexp.v8f16.v8i32(<8 x half> undef, <8 x i32> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v16f16 = call <16 x half> @llvm.ldexp.v16f16.v16i32(<16 x half> undef, <16 x i32> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %v17f16 = call <17 x half> @llvm.ldexp.v17f16.v17i32(<17 x half> undef, <17 x i32> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void |
| ; |
| ; GFX8PLUS-SIZE-LABEL: 'ldexp_f16_i32' |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.ldexp.f16.i32(half undef, i32 undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2f16 = call <2 x half> @llvm.ldexp.v2f16.v2i32(<2 x half> undef, <2 x i32> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %v3f16 = call <3 x half> @llvm.ldexp.v3f16.v3i32(<3 x half> undef, <3 x i32> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4f16 = call <4 x half> @llvm.ldexp.v4f16.v4i32(<4 x half> undef, <4 x i32> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %v5f16 = call <5 x half> @llvm.ldexp.v5f16.v5i32(<5 x half> undef, <5 x i32> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8f16 = call <8 x half> @llvm.ldexp.v8f16.v8i32(<8 x half> undef, <8 x i32> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16f16 = call <16 x half> @llvm.ldexp.v16f16.v16i32(<16 x half> undef, <16 x i32> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %v17f16 = call <17 x half> @llvm.ldexp.v17f16.v17i32(<17 x half> undef, <17 x i32> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void |
| ; |
| %f16 = call half @llvm.ldexp.f16.i32(half undef, i32 undef) |
| %v2f16 = call <2 x half> @llvm.ldexp.v2f16.v2i32(<2 x half> undef, <2 x i32> undef) |
| %v3f16 = call <3 x half> @llvm.ldexp.v3f16.v3i32(<3 x half> undef, <3 x i32> undef) |
| %v4f16 = call <4 x half> @llvm.ldexp.v4f16.v4i32(<4 x half> undef, <4 x i32> undef) |
| %v5f16 = call <5 x half> @llvm.ldexp.v5f16.v5i32(<5 x half> undef, <5 x i32> undef) |
| %v8f16 = call <8 x half> @llvm.ldexp.v8f16.v8i32(<8 x half> undef, <8 x i32> undef) |
| %v16f16 = call <16 x half> @llvm.ldexp.v16f16.v16i32(<16 x half> undef, <16 x i32> undef) |
| %v17f16 = call <17 x half> @llvm.ldexp.v17f16.v17i32(<17 x half> undef, <17 x i32> undef) |
| ret void |
| } |
| |
| define void @ldexp_f16_i16() { |
| ; GFX7-LABEL: 'ldexp_f16_i16' |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.ldexp.f16.i16(half undef, i16 undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2f16 = call <2 x half> @llvm.ldexp.v2f16.v2i16(<2 x half> undef, <2 x i16> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v3f16 = call <3 x half> @llvm.ldexp.v3f16.v3i16(<3 x half> undef, <3 x i16> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v4f16 = call <4 x half> @llvm.ldexp.v4f16.v4i16(<4 x half> undef, <4 x i16> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %v5f16 = call <5 x half> @llvm.ldexp.v5f16.v5i16(<5 x half> undef, <5 x i16> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v8f16 = call <8 x half> @llvm.ldexp.v8f16.v8i16(<8 x half> undef, <8 x i16> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v16f16 = call <16 x half> @llvm.ldexp.v16f16.v16i16(<16 x half> undef, <16 x i16> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %v17f16 = call <17 x half> @llvm.ldexp.v17f16.v17i16(<17 x half> undef, <17 x i16> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void |
| ; |
| ; GFX8PLUS-LABEL: 'ldexp_f16_i16' |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.ldexp.f16.i16(half undef, i16 undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2f16 = call <2 x half> @llvm.ldexp.v2f16.v2i16(<2 x half> undef, <2 x i16> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %v3f16 = call <3 x half> @llvm.ldexp.v3f16.v3i16(<3 x half> undef, <3 x i16> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4f16 = call <4 x half> @llvm.ldexp.v4f16.v4i16(<4 x half> undef, <4 x i16> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %v5f16 = call <5 x half> @llvm.ldexp.v5f16.v5i16(<5 x half> undef, <5 x i16> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8f16 = call <8 x half> @llvm.ldexp.v8f16.v8i16(<8 x half> undef, <8 x i16> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16f16 = call <16 x half> @llvm.ldexp.v16f16.v16i16(<16 x half> undef, <16 x i16> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %v17f16 = call <17 x half> @llvm.ldexp.v17f16.v17i16(<17 x half> undef, <17 x i16> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void |
| ; |
| ; GFX7-SIZE-LABEL: 'ldexp_f16_i16' |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.ldexp.f16.i16(half undef, i16 undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2f16 = call <2 x half> @llvm.ldexp.v2f16.v2i16(<2 x half> undef, <2 x i16> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v3f16 = call <3 x half> @llvm.ldexp.v3f16.v3i16(<3 x half> undef, <3 x i16> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v4f16 = call <4 x half> @llvm.ldexp.v4f16.v4i16(<4 x half> undef, <4 x i16> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %v5f16 = call <5 x half> @llvm.ldexp.v5f16.v5i16(<5 x half> undef, <5 x i16> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v8f16 = call <8 x half> @llvm.ldexp.v8f16.v8i16(<8 x half> undef, <8 x i16> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v16f16 = call <16 x half> @llvm.ldexp.v16f16.v16i16(<16 x half> undef, <16 x i16> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %v17f16 = call <17 x half> @llvm.ldexp.v17f16.v17i16(<17 x half> undef, <17 x i16> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void |
| ; |
| ; GFX8PLUS-SIZE-LABEL: 'ldexp_f16_i16' |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.ldexp.f16.i16(half undef, i16 undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2f16 = call <2 x half> @llvm.ldexp.v2f16.v2i16(<2 x half> undef, <2 x i16> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %v3f16 = call <3 x half> @llvm.ldexp.v3f16.v3i16(<3 x half> undef, <3 x i16> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4f16 = call <4 x half> @llvm.ldexp.v4f16.v4i16(<4 x half> undef, <4 x i16> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %v5f16 = call <5 x half> @llvm.ldexp.v5f16.v5i16(<5 x half> undef, <5 x i16> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8f16 = call <8 x half> @llvm.ldexp.v8f16.v8i16(<8 x half> undef, <8 x i16> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16f16 = call <16 x half> @llvm.ldexp.v16f16.v16i16(<16 x half> undef, <16 x i16> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %v17f16 = call <17 x half> @llvm.ldexp.v17f16.v17i16(<17 x half> undef, <17 x i16> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void |
| ; |
| %f16 = call half @llvm.ldexp.f16.i16(half undef, i16 undef) |
| %v2f16 = call <2 x half> @llvm.ldexp.v2f16.v2i16(<2 x half> undef, <2 x i16> undef) |
| %v3f16 = call <3 x half> @llvm.ldexp.v3f16.v3i16(<3 x half> undef, <3 x i16> undef) |
| %v4f16 = call <4 x half> @llvm.ldexp.v4f16.v4i16(<4 x half> undef, <4 x i16> undef) |
| %v5f16 = call <5 x half> @llvm.ldexp.v5f16.v5i16(<5 x half> undef, <5 x i16> undef) |
| %v8f16 = call <8 x half> @llvm.ldexp.v8f16.v8i16(<8 x half> undef, <8 x i16> undef) |
| %v16f16 = call <16 x half> @llvm.ldexp.v16f16.v16i16(<16 x half> undef, <16 x i16> undef) |
| %v17f16 = call <17 x half> @llvm.ldexp.v17f16.v17i16(<17 x half> undef, <17 x i16> undef) |
| ret void |
| } |
| |
| define void @ldexp_bf16() { |
| ; GFX7-LABEL: 'ldexp_bf16' |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.ldexp.bf16.i32(bfloat undef, i32 undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2bf16 = call <2 x bfloat> @llvm.ldexp.v2bf16.v2i32(<2 x bfloat> undef, <2 x i32> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v3bf16 = call <3 x bfloat> @llvm.ldexp.v3bf16.v3i32(<3 x bfloat> undef, <3 x i32> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v4bf16 = call <4 x bfloat> @llvm.ldexp.v4bf16.v4i32(<4 x bfloat> undef, <4 x i32> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %v5bf16 = call <5 x bfloat> @llvm.ldexp.v5bf16.v5i32(<5 x bfloat> undef, <5 x i32> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v8bf16 = call <8 x bfloat> @llvm.ldexp.v8bf16.v8i32(<8 x bfloat> undef, <8 x i32> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v16bf16 = call <16 x bfloat> @llvm.ldexp.v16bf16.v16i32(<16 x bfloat> undef, <16 x i32> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %v17bf16 = call <17 x bfloat> @llvm.ldexp.v17bf16.v17i32(<17 x bfloat> undef, <17 x i32> undef) |
| ; GFX7-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void |
| ; |
| ; GFX8PLUS-LABEL: 'ldexp_bf16' |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.ldexp.bf16.i32(bfloat undef, i32 undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2bf16 = call <2 x bfloat> @llvm.ldexp.v2bf16.v2i32(<2 x bfloat> undef, <2 x i32> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %v3bf16 = call <3 x bfloat> @llvm.ldexp.v3bf16.v3i32(<3 x bfloat> undef, <3 x i32> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4bf16 = call <4 x bfloat> @llvm.ldexp.v4bf16.v4i32(<4 x bfloat> undef, <4 x i32> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %v5bf16 = call <5 x bfloat> @llvm.ldexp.v5bf16.v5i32(<5 x bfloat> undef, <5 x i32> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8bf16 = call <8 x bfloat> @llvm.ldexp.v8bf16.v8i32(<8 x bfloat> undef, <8 x i32> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16bf16 = call <16 x bfloat> @llvm.ldexp.v16bf16.v16i32(<16 x bfloat> undef, <16 x i32> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %v17bf16 = call <17 x bfloat> @llvm.ldexp.v17bf16.v17i32(<17 x bfloat> undef, <17 x i32> undef) |
| ; GFX8PLUS-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void |
| ; |
| ; GFX7-SIZE-LABEL: 'ldexp_bf16' |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.ldexp.bf16.i32(bfloat undef, i32 undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2bf16 = call <2 x bfloat> @llvm.ldexp.v2bf16.v2i32(<2 x bfloat> undef, <2 x i32> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v3bf16 = call <3 x bfloat> @llvm.ldexp.v3bf16.v3i32(<3 x bfloat> undef, <3 x i32> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v4bf16 = call <4 x bfloat> @llvm.ldexp.v4bf16.v4i32(<4 x bfloat> undef, <4 x i32> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %v5bf16 = call <5 x bfloat> @llvm.ldexp.v5bf16.v5i32(<5 x bfloat> undef, <5 x i32> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v8bf16 = call <8 x bfloat> @llvm.ldexp.v8bf16.v8i32(<8 x bfloat> undef, <8 x i32> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v16bf16 = call <16 x bfloat> @llvm.ldexp.v16bf16.v16i32(<16 x bfloat> undef, <16 x i32> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %v17bf16 = call <17 x bfloat> @llvm.ldexp.v17bf16.v17i32(<17 x bfloat> undef, <17 x i32> undef) |
| ; GFX7-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void |
| ; |
| ; GFX8PLUS-SIZE-LABEL: 'ldexp_bf16' |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.ldexp.bf16.i32(bfloat undef, i32 undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2bf16 = call <2 x bfloat> @llvm.ldexp.v2bf16.v2i32(<2 x bfloat> undef, <2 x i32> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %v3bf16 = call <3 x bfloat> @llvm.ldexp.v3bf16.v3i32(<3 x bfloat> undef, <3 x i32> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4bf16 = call <4 x bfloat> @llvm.ldexp.v4bf16.v4i32(<4 x bfloat> undef, <4 x i32> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %v5bf16 = call <5 x bfloat> @llvm.ldexp.v5bf16.v5i32(<5 x bfloat> undef, <5 x i32> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8bf16 = call <8 x bfloat> @llvm.ldexp.v8bf16.v8i32(<8 x bfloat> undef, <8 x i32> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16bf16 = call <16 x bfloat> @llvm.ldexp.v16bf16.v16i32(<16 x bfloat> undef, <16 x i32> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %v17bf16 = call <17 x bfloat> @llvm.ldexp.v17bf16.v17i32(<17 x bfloat> undef, <17 x i32> undef) |
| ; GFX8PLUS-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void |
| ; |
| %bf16 = call bfloat @llvm.ldexp.bf16.i32(bfloat undef, i32 undef) |
| %v2bf16 = call <2 x bfloat> @llvm.ldexp.v2bf16.v2i32(<2 x bfloat> undef, <2 x i32> undef) |
| %v3bf16 = call <3 x bfloat> @llvm.ldexp.v3bf16.v3i32(<3 x bfloat> undef, <3 x i32> undef) |
| %v4bf16 = call <4 x bfloat> @llvm.ldexp.v4bf16.v4i32(<4 x bfloat> undef, <4 x i32> undef) |
| %v5bf16 = call <5 x bfloat> @llvm.ldexp.v5bf16.v5i32(<5 x bfloat> undef, <5 x i32> undef) |
| %v8bf16 = call <8 x bfloat> @llvm.ldexp.v8bf16.v8i32(<8 x bfloat> undef, <8 x i32> undef) |
| %v16bf16 = call <16 x bfloat> @llvm.ldexp.v16bf16.v16i32(<16 x bfloat> undef, <16 x i32> undef) |
| %v17bf16 = call <17 x bfloat> @llvm.ldexp.v17bf16.v17i32(<17 x bfloat> undef, <17 x i32> undef) |
| ret void |
| } |
| |
| define void @ldexp_f32() { |
| ; ALL-LABEL: 'ldexp_f32' |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f32 = call float @llvm.ldexp.f32.i32(float undef, i32 undef) |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2f32 = call <2 x float> @llvm.ldexp.v2f32.v2i32(<2 x float> undef, <2 x i32> undef) |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v3f32 = call <3 x float> @llvm.ldexp.v3f32.v3i32(<3 x float> undef, <3 x i32> undef) |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v4f32 = call <4 x float> @llvm.ldexp.v4f32.v4i32(<4 x float> undef, <4 x i32> undef) |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %v5f32 = call <5 x float> @llvm.ldexp.v5f32.v5i32(<5 x float> undef, <5 x i32> undef) |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8f32 = call <8 x float> @llvm.ldexp.v8f32.v8i32(<8 x float> undef, <8 x i32> undef) |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v16f32 = call <16 x float> @llvm.ldexp.v16f32.v16i32(<16 x float> undef, <16 x i32> undef) |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %v17f32 = call <17 x float> @llvm.ldexp.v17f32.v17i32(<17 x float> undef, <17 x i32> undef) |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void |
| ; |
| ; ALL-SIZE-LABEL: 'ldexp_f32' |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f32 = call float @llvm.ldexp.f32.i32(float undef, i32 undef) |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2f32 = call <2 x float> @llvm.ldexp.v2f32.v2i32(<2 x float> undef, <2 x i32> undef) |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v3f32 = call <3 x float> @llvm.ldexp.v3f32.v3i32(<3 x float> undef, <3 x i32> undef) |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v4f32 = call <4 x float> @llvm.ldexp.v4f32.v4i32(<4 x float> undef, <4 x i32> undef) |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %v5f32 = call <5 x float> @llvm.ldexp.v5f32.v5i32(<5 x float> undef, <5 x i32> undef) |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8f32 = call <8 x float> @llvm.ldexp.v8f32.v8i32(<8 x float> undef, <8 x i32> undef) |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v16f32 = call <16 x float> @llvm.ldexp.v16f32.v16i32(<16 x float> undef, <16 x i32> undef) |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %v17f32 = call <17 x float> @llvm.ldexp.v17f32.v17i32(<17 x float> undef, <17 x i32> undef) |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void |
| ; |
| %f32 = call float @llvm.ldexp.f32.i32(float undef, i32 undef) |
| %v2f32 = call <2 x float> @llvm.ldexp.v2f32.v2i32(<2 x float> undef, <2 x i32> undef) |
| %v3f32 = call <3 x float> @llvm.ldexp.v3f32.v3i32(<3 x float> undef, <3 x i32> undef) |
| %v4f32 = call <4 x float> @llvm.ldexp.v4f32.v4i32(<4 x float> undef, <4 x i32> undef) |
| %v5f32 = call <5 x float> @llvm.ldexp.v5f32.v5i32(<5 x float> undef, <5 x i32> undef) |
| %v8f32 = call <8 x float> @llvm.ldexp.v8f32.v8i32(<8 x float> undef, <8 x i32> undef) |
| %v16f32 = call <16 x float> @llvm.ldexp.v16f32.v16i32(<16 x float> undef, <16 x i32> undef) |
| %v17f32 = call <17 x float> @llvm.ldexp.v17f32.v17i32(<17 x float> undef, <17 x i32> undef) |
| ret void |
| } |
| |
| define void @ldexp_f64() { |
| ; ALL-LABEL: 'ldexp_f64' |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f64 = call double @llvm.ldexp.f64.i32(double undef, i32 undef) |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2f64 = call <2 x double> @llvm.ldexp.v2f64.v2i32(<2 x double> undef, <2 x i32> undef) |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v3f64 = call <3 x double> @llvm.ldexp.v3f64.v3i32(<3 x double> undef, <3 x i32> undef) |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v4f64 = call <4 x double> @llvm.ldexp.v4f64.v4i32(<4 x double> undef, <4 x i32> undef) |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %v5f64 = call <5 x double> @llvm.ldexp.v5f64.v5i32(<5 x double> undef, <5 x i32> undef) |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8f64 = call <8 x double> @llvm.ldexp.v8f64.v8i32(<8 x double> undef, <8 x i32> undef) |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v16f64 = call <16 x double> @llvm.ldexp.v16f64.v16i32(<16 x double> undef, <16 x i32> undef) |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %v17f64 = call <17 x double> @llvm.ldexp.v17f64.v17i32(<17 x double> undef, <17 x i32> undef) |
| ; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void |
| ; |
| ; ALL-SIZE-LABEL: 'ldexp_f64' |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f64 = call double @llvm.ldexp.f64.i32(double undef, i32 undef) |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2f64 = call <2 x double> @llvm.ldexp.v2f64.v2i32(<2 x double> undef, <2 x i32> undef) |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v3f64 = call <3 x double> @llvm.ldexp.v3f64.v3i32(<3 x double> undef, <3 x i32> undef) |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v4f64 = call <4 x double> @llvm.ldexp.v4f64.v4i32(<4 x double> undef, <4 x i32> undef) |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %v5f64 = call <5 x double> @llvm.ldexp.v5f64.v5i32(<5 x double> undef, <5 x i32> undef) |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8f64 = call <8 x double> @llvm.ldexp.v8f64.v8i32(<8 x double> undef, <8 x i32> undef) |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v16f64 = call <16 x double> @llvm.ldexp.v16f64.v16i32(<16 x double> undef, <16 x i32> undef) |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %v17f64 = call <17 x double> @llvm.ldexp.v17f64.v17i32(<17 x double> undef, <17 x i32> undef) |
| ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void |
| ; |
| %f64 = call double @llvm.ldexp.f64.i32(double undef, i32 undef) |
| %v2f64 = call <2 x double> @llvm.ldexp.v2f64.v2i32(<2 x double> undef, <2 x i32> undef) |
| %v3f64 = call <3 x double> @llvm.ldexp.v3f64.v3i32(<3 x double> undef, <3 x i32> undef) |
| %v4f64 = call <4 x double> @llvm.ldexp.v4f64.v4i32(<4 x double> undef, <4 x i32> undef) |
| %v5f64 = call <5 x double> @llvm.ldexp.v5f64.v5i32(<5 x double> undef, <5 x i32> undef) |
| %v8f64 = call <8 x double> @llvm.ldexp.v8f64.v8i32(<8 x double> undef, <8 x i32> undef) |
| %v16f64 = call <16 x double> @llvm.ldexp.v16f64.v16i32(<16 x double> undef, <16 x i32> undef) |
| %v17f64 = call <17 x double> @llvm.ldexp.v17f64.v17i32(<17 x double> undef, <17 x i32> undef) |
| ret void |
| } |
