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
68 lines
3.3 KiB
LLVM
68 lines
3.3 KiB
LLVM
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -amdgpu-spill-sgpr-to-vgpr=0 -stop-after prologepilog -verify-machineinstrs %s -o - | FileCheck -check-prefix=AFTER-PEI %s
|
|
|
|
; Test that the ScavengeFI is serialized in the SIMachineFunctionInfo.
|
|
|
|
; AFTER-PEI-LABEL: {{^}}name: scavenge_fi
|
|
; AFTER-PEI: machineFunctionInfo:
|
|
; AFTER-PEI-NEXT: explicitKernArgSize: 12
|
|
; AFTER-PEI-NEXT: maxKernArgAlign: 8
|
|
; AFTER-PEI-NEXT: ldsSize: 0
|
|
; AFTER-PEI-NEXT: gdsSize: 0
|
|
; AFTER-PEI-NEXT: dynLDSAlign: 1
|
|
; AFTER-PEI-NEXT: isEntryFunction: true
|
|
; AFTER-PEI-NEXT: isChainFunction: false
|
|
; AFTER-PEI-NEXT: memoryBound: false
|
|
; AFTER-PEI-NEXT: waveLimiter: false
|
|
; AFTER-PEI-NEXT: hasSpilledSGPRs: true
|
|
; AFTER-PEI-NEXT: hasSpilledVGPRs: false
|
|
; AFTER-PEI-NEXT: numWaveDispatchSGPRs: 0
|
|
; AFTER-PEI-NEXT: numWaveDispatchVGPRs: 0
|
|
; AFTER-PEI-NEXT: scratchRSrcReg: '$sgpr68_sgpr69_sgpr70_sgpr71'
|
|
; AFTER-PEI-NEXT: frameOffsetReg: '$fp_reg'
|
|
; AFTER-PEI-NEXT: stackPtrOffsetReg: '$sgpr32'
|
|
; AFTER-PEI-NEXT: bytesInStackArgArea: 0
|
|
; AFTER-PEI-NEXT: returnsVoid: true
|
|
; AFTER-PEI-NEXT: argumentInfo:
|
|
; AFTER-PEI-NEXT: privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
|
|
; AFTER-PEI-NEXT: kernargSegmentPtr: { reg: '$sgpr4_sgpr5' }
|
|
; AFTER-PEI-NEXT: workGroupIDX: { reg: '$sgpr6' }
|
|
; AFTER-PEI-NEXT: privateSegmentWaveByteOffset: { reg: '$sgpr7' }
|
|
; AFTER-PEI-NEXT: workItemIDX: { reg: '$vgpr0' }
|
|
; AFTER-PEI-NEXT: psInputAddr: 0
|
|
; AFTER-PEI-NEXT: psInputEnable: 0
|
|
; AFTER-PEI-NEXT: maxMemoryClusterDWords: 8
|
|
; AFTER-PEI-NEXT: mode:
|
|
; AFTER-PEI-NEXT: ieee: true
|
|
; AFTER-PEI-NEXT: dx10-clamp: true
|
|
; AFTER-PEI-NEXT: fp32-input-denormals: true
|
|
; AFTER-PEI-NEXT: fp32-output-denormals: true
|
|
; AFTER-PEI-NEXT: fp64-fp16-input-denormals: true
|
|
; AFTER-PEI-NEXT: fp64-fp16-output-denormals: true
|
|
; AFTER-PEI-NEXT: highBitsOf32BitAddress: 0
|
|
; AFTER-PEI-NEXT: occupancy: 5
|
|
; AFTER-PEI-NEXT: scavengeFI: '%stack.3'
|
|
; AFTER-PEI-NEXT: vgprForAGPRCopy: ''
|
|
; AFTER-PEI-NEXT: sgprForEXECCopy: ''
|
|
; AFTER-PEI-NEXT: longBranchReservedReg: ''
|
|
; AFTER-PEI-NEXT: hasInitWholeWave: false
|
|
; AFTER-PEI-NEXT: dynamicVGPRBlockSize: 0
|
|
; AFTER-PEI-NEXT: scratchReservedForDynamicVGPRs: 0
|
|
; AFTER-PEI-NEXT: numKernargPreloadSGPRs: 0
|
|
; AFTER-PEI-NEXT: isWholeWaveFunction: false
|
|
; AFTER-PEI-NEXT: minNumAGPRs: 4294967295
|
|
; AFTER-PEI-NEXT: body:
|
|
define amdgpu_kernel void @scavenge_fi(ptr addrspace(1) %out, i32 %in) #0 {
|
|
%wide.sgpr0 = call <32 x i32> asm sideeffect "; def $0", "=s" () #0
|
|
%wide.sgpr1 = call <32 x i32> asm sideeffect "; def $0", "=s" () #0
|
|
%wide.sgpr2 = call <32 x i32> asm sideeffect "; def $0", "=s" () #0
|
|
%wide.sgpr3 = call <32 x i32> asm sideeffect "; def $0", "=s" () #0
|
|
|
|
call void asm sideeffect "; use $0", "s"(<32 x i32> %wide.sgpr0) #0
|
|
call void asm sideeffect "; use $0", "s"(<32 x i32> %wide.sgpr1) #0
|
|
call void asm sideeffect "; use $0", "s"(<32 x i32> %wide.sgpr2) #0
|
|
call void asm sideeffect "; use $0", "s"(<32 x i32> %wide.sgpr3) #0
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-cluster-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-cluster-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-cluster-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" }
|