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
58 lines
2.0 KiB
LLVM
58 lines
2.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
|
|
; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s
|
|
|
|
; When optimize for size, the constant $858993459 is moved into a register,
|
|
; and use that register in following two andl instructions.
|
|
|
|
define i32 @cnt32_optsize(i32 %x) nounwind readnone optsize {
|
|
; CHECK-LABEL: cnt32_optsize:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: movl %edi, %eax
|
|
; CHECK-NEXT: shrl %eax
|
|
; CHECK-NEXT: andl $1431655765, %eax # imm = 0x55555555
|
|
; CHECK-NEXT: subl %eax, %edi
|
|
; CHECK-NEXT: movl $858993459, %eax # imm = 0x33333333
|
|
; CHECK-NEXT: movl %edi, %ecx
|
|
; CHECK-NEXT: andl %eax, %ecx
|
|
; CHECK-NEXT: shrl $2, %edi
|
|
; CHECK-NEXT: andl %eax, %edi
|
|
; CHECK-NEXT: addl %ecx, %edi
|
|
; CHECK-NEXT: movl %edi, %eax
|
|
; CHECK-NEXT: shrl $4, %eax
|
|
; CHECK-NEXT: addl %edi, %eax
|
|
; CHECK-NEXT: andl $252645135, %eax # imm = 0xF0F0F0F
|
|
; CHECK-NEXT: imull $16843009, %eax, %eax # imm = 0x1010101
|
|
; CHECK-NEXT: shrl $24, %eax
|
|
; CHECK-NEXT: retq
|
|
%cnt = tail call i32 @llvm.ctpop.i32(i32 %x)
|
|
ret i32 %cnt
|
|
}
|
|
|
|
; When optimize for speed, the constant $858993459 can be directly folded into
|
|
; two andl instructions.
|
|
|
|
define i32 @cnt32_optspeed(i32 %x) nounwind readnone {
|
|
; CHECK-LABEL: cnt32_optspeed:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: movl %edi, %eax
|
|
; CHECK-NEXT: shrl %eax
|
|
; CHECK-NEXT: andl $1431655765, %eax # imm = 0x55555555
|
|
; CHECK-NEXT: subl %eax, %edi
|
|
; CHECK-NEXT: movl %edi, %eax
|
|
; CHECK-NEXT: andl $858993459, %eax # imm = 0x33333333
|
|
; CHECK-NEXT: shrl $2, %edi
|
|
; CHECK-NEXT: andl $858993459, %edi # imm = 0x33333333
|
|
; CHECK-NEXT: addl %eax, %edi
|
|
; CHECK-NEXT: movl %edi, %eax
|
|
; CHECK-NEXT: shrl $4, %eax
|
|
; CHECK-NEXT: addl %edi, %eax
|
|
; CHECK-NEXT: andl $252645135, %eax # imm = 0xF0F0F0F
|
|
; CHECK-NEXT: imull $16843009, %eax, %eax # imm = 0x1010101
|
|
; CHECK-NEXT: shrl $24, %eax
|
|
; CHECK-NEXT: retq
|
|
%cnt = tail call i32 @llvm.ctpop.i32(i32 %x)
|
|
ret i32 %cnt
|
|
}
|
|
|
|
declare i32 @llvm.ctpop.i32(i32) nounwind readnone
|