derek/TheRock
1
0 Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
1a182e2dac58879f215c0fad0f5f78c76dcafe56
TheRock/compiler/amd-llvm/llvm/test/Analysis/CostModel/X86/arith-sminmax.ll
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
Details
CodeQL / Analyze (python) (push) Canceled after 0s
Details
pre-commit / pre-commit (push) Canceled after 0s
Details
Multi-Arch CI / setup (push) Canceled after 0s
Details
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Details
Setup (Multi-Arch) / setup (push) Canceled after 0s
Details
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Details
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
Details
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Details
Multi-Arch CI / CI Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Details
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Details
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

402 lines
43 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+sse2 | FileCheck %s -check-prefixes=SSE2
; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+ssse3 | FileCheck %s -check-prefixes=SSSE3
; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+sse4.2 | FileCheck %s -check-prefixes=SSE42
; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+avx | FileCheck %s -check-prefixes=AVX1
; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+avx2 | FileCheck %s -check-prefixes=AVX2
; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+avx512f | FileCheck %s -check-prefixes=AVX512F
; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+avx512vl,+avx512dq | FileCheck %s -check-prefixes=AVX512DQ
; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+avx512vl,+avx512bw | FileCheck %s -check-prefixes=AVX512BW
declare i64 @llvm.smax.i64(i64, i64)
declare <2 x i64> @llvm.smax.v2i64(<2 x i64>, <2 x i64>)
declare <4 x i64> @llvm.smax.v4i64(<4 x i64>, <4 x i64>)
declare <8 x i64> @llvm.smax.v8i64(<8 x i64>, <8 x i64>)
declare i32 @llvm.smax.i32(i32, i32)
declare <4 x i32> @llvm.smax.v4i32(<4 x i32>, <4 x i32>)
declare <8 x i32> @llvm.smax.v8i32(<8 x i32>, <8 x i32>)
declare <16 x i32> @llvm.smax.v16i32(<16 x i32>, <16 x i32>)
declare i16 @llvm.smax.i16(i16, i16)
declare <8 x i16> @llvm.smax.v8i16(<8 x i16>, <8 x i16>)
declare <16 x i16> @llvm.smax.v16i16(<16 x i16>, <16 x i16>)
declare <32 x i16> @llvm.smax.v32i16(<32 x i16>, <32 x i16>)
declare i8 @llvm.smax.i8(i8, i8)
declare <16 x i8> @llvm.smax.v16i8(<16 x i8>, <16 x i8>)
declare <32 x i8> @llvm.smax.v32i8(<32 x i8>, <32 x i8>)
declare <64 x i8> @llvm.smax.v64i8(<64 x i8>, <64 x i8>)
define i32 @smax(i32 %arg) {
; SSE2-LABEL: 'smax'
; SSE2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:4 CodeSize:15 Lat:8 SizeLat:15 for: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:8 CodeSize:30 Lat:16 SizeLat:30 for: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:16 CodeSize:60 Lat:32 SizeLat:60 for: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:2 CodeSize:5 Lat:4 SizeLat:5 for: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:4 CodeSize:10 Lat:8 SizeLat:10 for: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:8 CodeSize:20 Lat:16 SizeLat:20 for: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
; SSE2-NEXT: Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
; SSE2-NEXT: Cost Model: Found costs of 2 for: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
; SSE2-NEXT: Cost Model: Found costs of 4 for: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:2 CodeSize:5 Lat:4 SizeLat:5 for: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:4 CodeSize:10 Lat:8 SizeLat:10 for: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:8 CodeSize:20 Lat:16 SizeLat:20 for: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
; SSSE3-LABEL: 'smax'
; SSSE3-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:4 CodeSize:15 Lat:8 SizeLat:15 for: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:8 CodeSize:30 Lat:16 SizeLat:30 for: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:16 CodeSize:60 Lat:32 SizeLat:60 for: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:2 CodeSize:5 Lat:4 SizeLat:5 for: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:4 CodeSize:10 Lat:8 SizeLat:10 for: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:8 CodeSize:20 Lat:16 SizeLat:20 for: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
; SSSE3-NEXT: Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
; SSSE3-NEXT: Cost Model: Found costs of 2 for: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
; SSSE3-NEXT: Cost Model: Found costs of 4 for: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:2 CodeSize:5 Lat:4 SizeLat:5 for: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:4 CodeSize:10 Lat:8 SizeLat:10 for: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:8 CodeSize:20 Lat:16 SizeLat:20 for: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
; SSE42-LABEL: 'smax'
; SSE42-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
; SSE42-NEXT: Cost Model: Found costs of RThru:3 CodeSize:2 Lat:7 SizeLat:3 for: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
; SSE42-NEXT: Cost Model: Found costs of RThru:6 CodeSize:4 Lat:14 SizeLat:6 for: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
; SSE42-NEXT: Cost Model: Found costs of RThru:12 CodeSize:8 Lat:28 SizeLat:12 for: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
; SSE42-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
; SSE42-NEXT: Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
; SSE42-NEXT: Cost Model: Found costs of 2 for: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
; SSE42-NEXT: Cost Model: Found costs of 4 for: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
; SSE42-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
; SSE42-NEXT: Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
; SSE42-NEXT: Cost Model: Found costs of 2 for: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
; SSE42-NEXT: Cost Model: Found costs of 4 for: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
; SSE42-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
; SSE42-NEXT: Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
; SSE42-NEXT: Cost Model: Found costs of 2 for: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
; SSE42-NEXT: Cost Model: Found costs of 4 for: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
; SSE42-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
; AVX1-LABEL: 'smax'
; AVX1-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:3 CodeSize:2 Lat:7 SizeLat:4 for: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:6 CodeSize:6 Lat:9 SizeLat:12 for: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:12 CodeSize:12 Lat:18 SizeLat:24 for: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
; AVX1-NEXT: Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
; AVX1-NEXT: Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
; AVX1-NEXT: Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
; AVX2-LABEL: 'smax'
; AVX2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:7 SizeLat:3 for: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:7 SizeLat:3 for: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:14 SizeLat:6 for: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
; AVX2-NEXT: Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
; AVX2-NEXT: Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
; AVX2-NEXT: Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
; AVX512F-LABEL: 'smax'
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
; AVX512F-NEXT: Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
; AVX512F-NEXT: Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
; AVX512F-NEXT: Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
; AVX512F-NEXT: Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
; AVX512DQ-LABEL: 'smax'
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
; AVX512DQ-NEXT: Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
; AVX512DQ-NEXT: Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
; AVX512DQ-NEXT: Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
; AVX512BW-LABEL: 'smax'
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
; AVX512BW-NEXT: Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
; AVX512BW-NEXT: Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
; AVX512BW-NEXT: Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX512BW-NEXT: Cost Model: Found costs of 1 for: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
; AVX512BW-NEXT: Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found costs of 1 for: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
%I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
%V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
%V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
%V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
%I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
%V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
%V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
%V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
%I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
%V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
%V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
%V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
%I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
%V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
%V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
%V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
ret i32 undef
}
declare i64 @llvm.smin.i64(i64, i64)
declare <2 x i64> @llvm.smin.v2i64(<2 x i64>, <2 x i64>)
declare <4 x i64> @llvm.smin.v4i64(<4 x i64>, <4 x i64>)
declare <8 x i64> @llvm.smin.v8i64(<8 x i64>, <8 x i64>)
declare i32 @llvm.smin.i32(i32, i32)
declare <4 x i32> @llvm.smin.v4i32(<4 x i32>, <4 x i32>)
declare <8 x i32> @llvm.smin.v8i32(<8 x i32>, <8 x i32>)
declare <16 x i32> @llvm.smin.v16i32(<16 x i32>, <16 x i32>)
declare i16 @llvm.smin.i16(i16, i16)
declare <8 x i16> @llvm.smin.v8i16(<8 x i16>, <8 x i16>)
declare <16 x i16> @llvm.smin.v16i16(<16 x i16>, <16 x i16>)
declare <32 x i16> @llvm.smin.v32i16(<32 x i16>, <32 x i16>)
declare i8 @llvm.smin.i8(i8, i8)
declare <16 x i8> @llvm.smin.v16i8(<16 x i8>, <16 x i8>)
declare <32 x i8> @llvm.smin.v32i8(<32 x i8>, <32 x i8>)
declare <64 x i8> @llvm.smin.v64i8(<64 x i8>, <64 x i8>)
define i32 @smin(i32 %arg) {
; SSE2-LABEL: 'smin'
; SSE2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:4 CodeSize:15 Lat:8 SizeLat:15 for: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:8 CodeSize:30 Lat:16 SizeLat:30 for: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:16 CodeSize:60 Lat:32 SizeLat:60 for: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:2 CodeSize:5 Lat:4 SizeLat:5 for: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:4 CodeSize:10 Lat:8 SizeLat:10 for: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:8 CodeSize:20 Lat:16 SizeLat:20 for: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
; SSE2-NEXT: Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
; SSE2-NEXT: Cost Model: Found costs of 2 for: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
; SSE2-NEXT: Cost Model: Found costs of 4 for: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:2 CodeSize:5 Lat:4 SizeLat:5 for: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:4 CodeSize:10 Lat:8 SizeLat:10 for: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:8 CodeSize:20 Lat:16 SizeLat:20 for: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
; SSE2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
; SSSE3-LABEL: 'smin'
; SSSE3-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:4 CodeSize:15 Lat:8 SizeLat:15 for: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:8 CodeSize:30 Lat:16 SizeLat:30 for: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:16 CodeSize:60 Lat:32 SizeLat:60 for: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:2 CodeSize:5 Lat:4 SizeLat:5 for: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:4 CodeSize:10 Lat:8 SizeLat:10 for: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:8 CodeSize:20 Lat:16 SizeLat:20 for: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
; SSSE3-NEXT: Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
; SSSE3-NEXT: Cost Model: Found costs of 2 for: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
; SSSE3-NEXT: Cost Model: Found costs of 4 for: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:2 CodeSize:5 Lat:4 SizeLat:5 for: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:4 CodeSize:10 Lat:8 SizeLat:10 for: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:8 CodeSize:20 Lat:16 SizeLat:20 for: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
; SSSE3-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
; SSE42-LABEL: 'smin'
; SSE42-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
; SSE42-NEXT: Cost Model: Found costs of RThru:3 CodeSize:2 Lat:7 SizeLat:3 for: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
; SSE42-NEXT: Cost Model: Found costs of RThru:6 CodeSize:4 Lat:14 SizeLat:6 for: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
; SSE42-NEXT: Cost Model: Found costs of RThru:12 CodeSize:8 Lat:28 SizeLat:12 for: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
; SSE42-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
; SSE42-NEXT: Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
; SSE42-NEXT: Cost Model: Found costs of 2 for: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
; SSE42-NEXT: Cost Model: Found costs of 4 for: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
; SSE42-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
; SSE42-NEXT: Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
; SSE42-NEXT: Cost Model: Found costs of 2 for: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
; SSE42-NEXT: Cost Model: Found costs of 4 for: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
; SSE42-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
; SSE42-NEXT: Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
; SSE42-NEXT: Cost Model: Found costs of 2 for: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
; SSE42-NEXT: Cost Model: Found costs of 4 for: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
; SSE42-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
; AVX1-LABEL: 'smin'
; AVX1-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:3 CodeSize:2 Lat:7 SizeLat:3 for: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:6 CodeSize:6 Lat:9 SizeLat:12 for: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:12 CodeSize:12 Lat:18 SizeLat:24 for: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
; AVX1-NEXT: Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
; AVX1-NEXT: Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
; AVX1-NEXT: Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
; AVX1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
; AVX2-LABEL: 'smin'
; AVX2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:7 SizeLat:3 for: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:7 SizeLat:3 for: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:14 SizeLat:6 for: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
; AVX2-NEXT: Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
; AVX2-NEXT: Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
; AVX2-NEXT: Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
; AVX2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
; AVX512F-LABEL: 'smin'
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
; AVX512F-NEXT: Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
; AVX512F-NEXT: Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
; AVX512F-NEXT: Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
; AVX512F-NEXT: Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
; AVX512F-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
; AVX512DQ-LABEL: 'smin'
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
; AVX512DQ-NEXT: Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
; AVX512DQ-NEXT: Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
; AVX512DQ-NEXT: Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
; AVX512BW-LABEL: 'smin'
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
; AVX512BW-NEXT: Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
; AVX512BW-NEXT: Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
; AVX512BW-NEXT: Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
; AVX512BW-NEXT: Cost Model: Found costs of 1 for: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
; AVX512BW-NEXT: Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found costs of 1 for: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
%I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
%V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
%V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
%V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
%I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
%V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
%V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
%V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
%I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
%V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
%V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
%V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
%I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
%V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
%V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
%V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
ret i32 undef
}
Reference in new issue View Git Blame Copy Permalink