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
53 lines
3.4 KiB
LLVM
53 lines
3.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -stop-after=si-fix-sgpr-copies < %s | FileCheck %s
|
|
|
|
; FIXME: This should merge with
|
|
; tail-call-uniform-target-in-vgprs-issue110930.ll. This is split
|
|
; because all functions involving convergence tokens will fail the
|
|
; machine verifier after register allocation.
|
|
|
|
define void @tail_call_uniform_vgpr_value_convergence_tokens() #0 {
|
|
; CHECK-LABEL: name: tail_call_uniform_vgpr_value_convergence_tokens
|
|
; CHECK: bb.0 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr31
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr31
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
|
|
; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr13
|
|
; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
|
|
; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
|
|
; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
|
|
; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64 = COPY $sgpr6_sgpr7
|
|
; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
|
|
; CHECK-NEXT: [[CONVERGENCECTRL_ENTRY:%[0-9]+]]:sreg_64 = CONVERGENCECTRL_ENTRY
|
|
; CHECK-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
|
; CHECK-NEXT: [[DS_READ_B64_gfx9_:%[0-9]+]]:vreg_64 = DS_READ_B64_gfx9 killed [[V_MOV_B32_e32_]], 0, 0, implicit $exec :: (load (s64) from `ptr addrspace(3) null`, addrspace 3)
|
|
; CHECK-NEXT: [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[DS_READ_B64_gfx9_]].sub1
|
|
; CHECK-NEXT: CONVERGENCECTRL_GLUE [[CONVERGENCECTRL_ENTRY]]
|
|
; CHECK-NEXT: [[COPY10:%[0-9]+]]:vgpr_32 = COPY [[COPY9]]
|
|
; CHECK-NEXT: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 killed [[COPY10]], implicit $exec, implicit [[CONVERGENCECTRL_ENTRY]]
|
|
; CHECK-NEXT: [[COPY11:%[0-9]+]]:vgpr_32 = COPY [[DS_READ_B64_gfx9_]].sub0
|
|
; CHECK-NEXT: CONVERGENCECTRL_GLUE [[CONVERGENCECTRL_ENTRY]]
|
|
; CHECK-NEXT: [[COPY12:%[0-9]+]]:vgpr_32 = COPY [[COPY11]]
|
|
; CHECK-NEXT: [[V_READFIRSTLANE_B32_1:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 killed [[COPY12]], implicit $exec, implicit [[CONVERGENCECTRL_ENTRY]]
|
|
; CHECK-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE killed [[V_READFIRSTLANE_B32_1]], %subreg.sub0, killed [[V_READFIRSTLANE_B32_]], %subreg.sub1
|
|
; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY8]]
|
|
; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY7]]
|
|
; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY6]]
|
|
; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY5]]
|
|
; CHECK-NEXT: $sgpr12 = COPY [[COPY4]]
|
|
; CHECK-NEXT: $sgpr13 = COPY [[COPY3]]
|
|
; CHECK-NEXT: $sgpr14 = COPY [[COPY2]]
|
|
; CHECK-NEXT: $sgpr15 = COPY [[COPY1]]
|
|
; CHECK-NEXT: $vgpr31 = COPY [[COPY]]
|
|
; CHECK-NEXT: CONVERGENCECTRL_GLUE [[CONVERGENCECTRL_ENTRY]]
|
|
; CHECK-NEXT: SI_TCRETURN killed [[REG_SEQUENCE]], 0, 0, csr_amdgpu, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31, implicit [[CONVERGENCECTRL_ENTRY]]
|
|
%t = call token @llvm.experimental.convergence.entry()
|
|
%fptr = load ptr, ptr addrspace(3) zeroinitializer, align 8
|
|
tail call void %fptr() #0 [ "convergencectrl"(token %t) ]
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { convergent }
|