derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
87 lines
5.9 KiB
LLVM
87 lines
5.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
|
|
; RUN: opt -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output -mtriple=thumbv8.1m.main-none-eabi -mattr=+mve < %s | FileCheck %s --check-prefix=MVE
|
|
|
|
target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
|
|
|
|
declare i64 @llvm.abs.i64(i64, i1)
|
|
declare <2 x i64> @llvm.abs.v2i64(<2 x i64>, i1)
|
|
declare <4 x i64> @llvm.abs.v4i64(<4 x i64>, i1)
|
|
declare <8 x i64> @llvm.abs.v8i64(<8 x i64>, i1)
|
|
|
|
declare i32 @llvm.abs.i32(i32, i1)
|
|
declare <2 x i32> @llvm.abs.v2i32(<2 x i32>, i1)
|
|
declare <4 x i32> @llvm.abs.v4i32(<4 x i32>, i1)
|
|
declare <8 x i32> @llvm.abs.v8i32(<8 x i32>, i1)
|
|
declare <16 x i32> @llvm.abs.v16i32(<16 x i32>, i1)
|
|
|
|
declare i16 @llvm.abs.i16(i16, i1)
|
|
declare <2 x i16> @llvm.abs.v2i16(<2 x i16>, i1)
|
|
declare <4 x i16> @llvm.abs.v4i16(<4 x i16>, i1)
|
|
declare <8 x i16> @llvm.abs.v8i16(<8 x i16>, i1)
|
|
declare <16 x i16> @llvm.abs.v16i16(<16 x i16>, i1)
|
|
declare <32 x i16> @llvm.abs.v32i16(<32 x i16>, i1)
|
|
|
|
declare i8 @llvm.abs.i8(i8, i1)
|
|
declare <2 x i8> @llvm.abs.v2i8(<2 x i8>, i1)
|
|
declare <4 x i8> @llvm.abs.v4i8(<4 x i8>, i1)
|
|
declare <8 x i8> @llvm.abs.v8i8(<8 x i8>, i1)
|
|
declare <16 x i8> @llvm.abs.v16i8(<16 x i8>, i1)
|
|
declare <32 x i8> @llvm.abs.v32i8(<32 x i8>, i1)
|
|
declare <64 x i8> @llvm.abs.v64i8(<64 x i8>, i1)
|
|
|
|
define i32 @abs(i32 %arg) {
|
|
; MVE-LABEL: 'abs'
|
|
; MVE-NEXT: Cost Model: Found costs of 4 for: %I64 = call i64 @llvm.abs.i64(i64 undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:74 CodeSize:55 Lat:74 SizeLat:74 for: %V2I64 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:148 CodeSize:110 Lat:148 SizeLat:148 for: %V4I64 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:296 CodeSize:220 Lat:296 SizeLat:296 for: %V8I64 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of 2 for: %I32 = call i32 @llvm.abs.i32(i32 undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:40 CodeSize:29 Lat:40 SizeLat:40 for: %V2I32 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 for: %V4I32 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 for: %V8I32 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:8 CodeSize:4 Lat:8 SizeLat:8 for: %V16I32 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of 2 for: %I16 = call i16 @llvm.abs.i16(i16 undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:40 CodeSize:29 Lat:40 SizeLat:40 for: %V2I16 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 for: %V4I16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 for: %V8I16 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 for: %V16I16 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:8 CodeSize:4 Lat:8 SizeLat:8 for: %V32I16 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of 2 for: %I8 = call i8 @llvm.abs.i8(i8 undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:40 CodeSize:29 Lat:40 SizeLat:40 for: %V2I8 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 for: %V4I8 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 for: %V8I8 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 for: %V16I8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 for: %V32I8 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:8 CodeSize:4 Lat:8 SizeLat:8 for: %V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 false)
|
|
; MVE-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
|
|
;
|
|
%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)
|
|
%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)
|
|
%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)
|
|
%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)
|
|
%V64I8 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 false)
|
|
|
|
ret i32 undef
|
|
}
|
|
|