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
63 lines
3.3 KiB
LLVM
63 lines
3.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 2
|
|
; RUN: opt -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output -mtriple=aarch64--linux-gnu < %s | FileCheck %s
|
|
|
|
; Verify the cost of bswap instructions.
|
|
|
|
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
|
|
|
|
declare i16 @llvm.bswap.i16(i16)
|
|
declare i32 @llvm.bswap.i32(i32)
|
|
declare i64 @llvm.bswap.i64(i64)
|
|
|
|
declare <4 x i16> @llvm.bswap.v4i16(<4 x i16>)
|
|
declare <8 x i16> @llvm.bswap.v8i16(<8 x i16>)
|
|
declare <16 x i16> @llvm.bswap.v16i16(<16 x i16>)
|
|
declare <2 x i32> @llvm.bswap.v2i32(<2 x i32>)
|
|
declare <4 x i32> @llvm.bswap.v4i32(<4 x i32>)
|
|
declare <8 x i32> @llvm.bswap.v8i32(<8 x i32>)
|
|
declare <2 x i64> @llvm.bswap.v2i64(<2 x i64>)
|
|
declare <4 x i64> @llvm.bswap.v4i64(<4 x i64>)
|
|
declare <3 x i32> @llvm.bswap.v3i32(<3 x i32>)
|
|
declare <4 x i48> @llvm.bswap.v4i48(<4 x i48>)
|
|
|
|
define void @scalar() {
|
|
; CHECK-LABEL: 'scalar'
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %b16 = call i16 @llvm.bswap.i16(i16 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %b32 = call i32 @llvm.bswap.i32(i32 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %b64 = call i64 @llvm.bswap.i64(i64 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%b16 = call i16 @llvm.bswap.i16(i16 undef)
|
|
%b32 = call i32 @llvm.bswap.i32(i32 undef)
|
|
%b64 = call i64 @llvm.bswap.i64(i64 undef)
|
|
ret void
|
|
}
|
|
|
|
define void @neon() {
|
|
; CHECK-LABEL: 'neon'
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %v4i16 = call <4 x i16> @llvm.bswap.v4i16(<4 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %v8i16 = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %v16i16 = call <16 x i16> @llvm.bswap.v16i16(<16 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %v2i32 = call <2 x i32> @llvm.bswap.v2i32(<2 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %v4i32 = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %v8i32 = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %v2i64 = call <2 x i64> @llvm.bswap.v2i64(<2 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %v4i64 = call <4 x i64> @llvm.bswap.v4i64(<4 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %v3i32 = call <3 x i32> @llvm.bswap.v3i32(<3 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %v4i48 = call <4 x i48> @llvm.bswap.v4i48(<4 x i48> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%v4i16 = call <4 x i16> @llvm.bswap.v4i16(<4 x i16> undef)
|
|
%v8i16 = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> undef)
|
|
%v16i16 = call <16 x i16> @llvm.bswap.v16i16(<16 x i16> undef)
|
|
%v2i32 = call <2 x i32> @llvm.bswap.v2i32(<2 x i32> undef)
|
|
%v4i32 = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> undef)
|
|
%v8i32 = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> undef)
|
|
%v2i64 = call <2 x i64> @llvm.bswap.v2i64(<2 x i64> undef)
|
|
%v4i64 = call <4 x i64> @llvm.bswap.v4i64(<4 x i64> undef)
|
|
|
|
%v3i32 = call <3 x i32> @llvm.bswap.v3i32(<3 x i32> undef)
|
|
%v4i48 = call <4 x i48> @llvm.bswap.v4i48(<4 x i48> undef)
|
|
ret void
|
|
}
|