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
57 lines
2.9 KiB
LLVM
57 lines
2.9 KiB
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=gfx906 -mattr=+wavefrontsize64 -stop-after=amdgpu-remove-incompatible-functions\
|
|
; RUN: -pass-remarks=amdgpu-remove-incompatible-functions < %s 2>%t | FileCheck -check-prefixes=GFX906 %s
|
|
; RUN: FileCheck --check-prefix=WARN-GFX906 %s < %t
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx906 -mattr=+wavefrontsize64 < %s
|
|
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx90a -mattr=+wavefrontsize64 -stop-after=amdgpu-remove-incompatible-functions\
|
|
; RUN: -pass-remarks=amdgpu-remove-incompatible-functions < %s 2>%t | FileCheck -check-prefixes=GFX90A %s
|
|
; RUN: FileCheck --check-prefix=WARN-GFX90A %s < %t
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx90a -mattr=+wavefrontsize64 < %s
|
|
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx1011 -mattr=-wavefrontsize32,+wavefrontsize64 -stop-after=amdgpu-remove-incompatible-functions\
|
|
; RUN: -pass-remarks=amdgpu-remove-incompatible-functions < %s 2>%t | FileCheck -check-prefixes=GFX10 %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx1011 -mattr=-wavefrontsize32,+wavefrontsize64 < %s
|
|
|
|
; RUN: llc -enable-new-pm -mtriple=amdgcn -mcpu=gfx1011 -mattr=-wavefrontsize32,+wavefrontsize64 -stop-after=amdgpu-remove-incompatible-functions\
|
|
; RUN: -pass-remarks=amdgpu-remove-incompatible-functions < %s 2>%t | FileCheck -check-prefixes=GFX10 %s
|
|
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=-wavefrontsize32,+wavefrontsize64 -stop-after=amdgpu-remove-incompatible-functions\
|
|
; RUN: -pass-remarks=amdgpu-remove-incompatible-functions < %s 2>%t | FileCheck -check-prefixes=GFX11 %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=-wavefrontsize32,+wavefrontsize64 < %s
|
|
|
|
; RUN: llc -enable-new-pm -mtriple=amdgcn -mcpu=gfx1100 -mattr=-wavefrontsize32,+wavefrontsize64 -stop-after=amdgpu-remove-incompatible-functions\
|
|
; RUN: -pass-remarks=amdgpu-remove-incompatible-functions < %s 2>%t | FileCheck -check-prefixes=GFX11 %s
|
|
|
|
; WARN-GFX906: removing function 'needs_wavefrontsize32': +wavefrontsize32 is not supported on the current target
|
|
; WARN-GFX906-NOT: not supported
|
|
|
|
; WARN-GFX90A: removing function 'needs_wavefrontsize32': +wavefrontsize32 is not supported on the current target
|
|
; WARN-GFX90A-NOT: not supported
|
|
|
|
define void @needs_wavefrontsize32(ptr %out) #0 {
|
|
; GFX906-NOT: @needs_wavefrontsize32
|
|
; GFX90A-NOT: @needs_wavefrontsize32
|
|
; GFX10: define void @needs_wavefrontsize32(
|
|
; GFX11: define void @needs_wavefrontsize32(
|
|
%1 = tail call i32 @llvm.read_register.i32(metadata !0)
|
|
%2 = tail call i32 @llvm.ctpop.i32(i32 %1)
|
|
store i32 %2, ptr %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define void @caller(ptr %out) {
|
|
; GFX906: call void null(
|
|
; GFX90A: call void null(
|
|
; GFX10: call void @needs_wavefrontsize32(
|
|
; GFX11: call void @needs_wavefrontsize32(
|
|
call void @needs_wavefrontsize32(ptr %out)
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.read_register.i32(metadata)
|
|
declare i32 @llvm.ctpop.i32(i32)
|
|
|
|
!0 = !{!"exec_lo"}
|
|
|
|
attributes #0 = { "target-features"="+wavefrontsize32" }
|