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
51 lines
1.7 KiB
LLVM
51 lines
1.7 KiB
LLVM
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx908 < %s | FileCheck -check-prefixes=CHECK,GFX908 %s
|
|
; RUN: not llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a < %s 2> %t.err | FileCheck -check-prefixes=CHECK,GFX90A %s
|
|
; RUN: FileCheck --implicit-check-not=error -check-prefix=ERR < %t.err %s
|
|
|
|
; Test undefined behavior where a function ends up needing AGPRs that
|
|
; was marked with "amdgpu-agpr-alloc="="0". There should be no asserts.
|
|
|
|
; TODO: Should this be an error, or let UB happen?
|
|
|
|
; ERR: error: <unknown>:0:0: no registers from class available to allocate in function 'kernel_illegal_agpr_use_asm'
|
|
; ERR: error: <unknown>:0:0: no registers from class available to allocate in function 'func_illegal_agpr_use_asm'
|
|
|
|
; CHECK: {{^}}kernel_illegal_agpr_use_asm:
|
|
; CHECK: ; use a0
|
|
|
|
; CHECK: NumVgprs: 0
|
|
; CHECK: NumAgprs: 1
|
|
define amdgpu_kernel void @kernel_illegal_agpr_use_asm() #0 {
|
|
call void asm sideeffect "; use $0", "a"(i32 poison)
|
|
ret void
|
|
}
|
|
|
|
; CHECK: {{^}}func_illegal_agpr_use_asm:
|
|
; CHECK: ; use a0
|
|
|
|
; CHECK: NumVgprs: 0
|
|
; CHECK: NumAgprs: 1
|
|
define void @func_illegal_agpr_use_asm() #0 {
|
|
call void asm sideeffect "; use $0", "a"(i32 poison)
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}kernel_calls_mfma.f32.32x32x1f32:
|
|
; GFX908: v_accvgpr_write_b32
|
|
; GFX90A-NOT: v_accvgpr_write_b32
|
|
|
|
; GFX908: NumVgprs: 5
|
|
; GFX908: NumAgprs: 32
|
|
; GFX90A: NumVgprs: 35
|
|
; GFX90A: NumAgprs: 0
|
|
|
|
; GFX908: TotalNumVgprs: 32
|
|
; GFX90A: TotalNumVgprs: 35
|
|
define amdgpu_kernel void @kernel_calls_mfma.f32.32x32x1f32(ptr addrspace(1) %out, float %a, float %b, <32 x float> %c) #0 {
|
|
%result = call <32 x float> @llvm.amdgcn.mfma.f32.32x32x1f32(float %a, float %b, <32 x float> %c, i32 0, i32 0, i32 0)
|
|
store <32 x float> %result, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { "amdgpu-agpr-alloc"="0" }
|