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
72 lines
2.7 KiB
LLVM
72 lines
2.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -passes="require<profile-summary>,function(codegenprepare)" < %s | FileCheck %s --check-prefix=SLOW
|
|
; RUN: opt -S -passes="require<profile-summary>,function(codegenprepare)" -mattr=+bmi < %s | FileCheck %s --check-prefix=FAST_TZ
|
|
; RUN: opt -S -passes="require<profile-summary>,function(codegenprepare)" -mattr=+lzcnt < %s | FileCheck %s --check-prefix=FAST_LZ
|
|
|
|
; RUN: opt -S -enable-debugify -passes="require<profile-summary>,function(codegenprepare)" < %s | FileCheck %s --check-prefix=DEBUGINFO
|
|
|
|
target triple = "x86_64-unknown-unknown"
|
|
target datalayout = "e-n32:64"
|
|
|
|
; If the intrinsic is cheap, nothing should change.
|
|
; If the intrinsic is expensive, check if the input is zero to avoid the call.
|
|
; This is undoing speculation that may have been created by SimplifyCFG + InstCombine.
|
|
|
|
define i64 @cttz(i64 %A) {
|
|
; SLOW-LABEL: @cttz(
|
|
; SLOW-NEXT: entry:
|
|
; SLOW-NEXT: [[Z:%.*]] = call i64 @llvm.cttz.i64(i64 [[A:%.*]], i1 false)
|
|
; SLOW-NEXT: ret i64 [[Z]]
|
|
;
|
|
; FAST_TZ-LABEL: @cttz(
|
|
; FAST_TZ-NEXT: entry:
|
|
; FAST_TZ-NEXT: [[Z:%.*]] = call i64 @llvm.cttz.i64(i64 [[A:%.*]], i1 false)
|
|
; FAST_TZ-NEXT: ret i64 [[Z]]
|
|
;
|
|
; FAST_LZ-LABEL: @cttz(
|
|
; FAST_LZ-NEXT: entry:
|
|
; FAST_LZ-NEXT: [[Z:%.*]] = call i64 @llvm.cttz.i64(i64 [[A:%.*]], i1 false)
|
|
; FAST_LZ-NEXT: ret i64 [[Z]]
|
|
;
|
|
; DEBUGINFO-LABEL: @cttz(
|
|
; DEBUGINFO-NEXT: entry:
|
|
; DEBUGINFO-NEXT: [[Z:%.*]] = call i64 @llvm.cttz.i64(i64 [[A:%.*]], i1 false), !dbg [[DBG11:![0-9]+]]
|
|
; DEBUGINFO-NEXT: #dbg_value(i64 [[Z]], [[META9:![0-9]+]], !DIExpression(), [[DBG11]])
|
|
; DEBUGINFO-NEXT: ret i64 [[Z]], !dbg [[DBG12:![0-9]+]]
|
|
;
|
|
entry:
|
|
%z = call i64 @llvm.cttz.i64(i64 %A, i1 false)
|
|
ret i64 %z
|
|
}
|
|
|
|
define i64 @ctlz(i64 %A) {
|
|
; SLOW-LABEL: @ctlz(
|
|
; SLOW-NEXT: entry:
|
|
; SLOW-NEXT: [[Z:%.*]] = call i64 @llvm.ctlz.i64(i64 [[A:%.*]], i1 false)
|
|
; SLOW-NEXT: ret i64 [[Z]]
|
|
;
|
|
; FAST_TZ-LABEL: @ctlz(
|
|
; FAST_TZ-NEXT: entry:
|
|
; FAST_TZ-NEXT: [[Z:%.*]] = call i64 @llvm.ctlz.i64(i64 [[A:%.*]], i1 false)
|
|
; FAST_TZ-NEXT: ret i64 [[Z]]
|
|
;
|
|
; FAST_LZ-LABEL: @ctlz(
|
|
; FAST_LZ-NEXT: entry:
|
|
; FAST_LZ-NEXT: [[Z:%.*]] = call i64 @llvm.ctlz.i64(i64 [[A:%.*]], i1 false)
|
|
; FAST_LZ-NEXT: ret i64 [[Z]]
|
|
;
|
|
; DEBUGINFO-LABEL: @ctlz(
|
|
; DEBUGINFO-NEXT: entry:
|
|
; DEBUGINFO-NEXT: [[Z:%.*]] = call i64 @llvm.ctlz.i64(i64 [[A:%.*]], i1 false), !dbg [[DBG16:![0-9]+]]
|
|
; DEBUGINFO-NEXT: #dbg_value(i64 [[Z]], [[META15:![0-9]+]], !DIExpression(), [[DBG16]])
|
|
; DEBUGINFO-NEXT: ret i64 [[Z]], !dbg [[DBG17:![0-9]+]]
|
|
;
|
|
entry:
|
|
%z = call i64 @llvm.ctlz.i64(i64 %A, i1 false)
|
|
ret i64 %z
|
|
}
|
|
|
|
declare i64 @llvm.cttz.i64(i64, i1)
|
|
declare i64 @llvm.ctlz.i64(i64, i1)
|
|
|