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
138 lines
9.9 KiB
LLVM
138 lines
9.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 2
|
|
; RUN: llc --global-isel=1 -mtriple=amdgcn--amdpal -mcpu=gfx1100 -stop-after=irtranslator %s -o - | FileCheck %s --check-prefix=GFX11
|
|
; RUN: llc --global-isel=1 -mtriple=amdgcn--amdpal -mcpu=gfx1030 -stop-after=irtranslator %s -o - | FileCheck %s --check-prefix=GFX10
|
|
|
|
declare amdgpu_cs_chain void @callee(<3 x i32> inreg, { i32, ptr addrspace(5), i32, i32 })
|
|
declare amdgpu_cs_chain_preserve void @callee_preserve(<3 x i32> inreg, { i32, ptr addrspace(5), i32, i32 })
|
|
declare void @llvm.amdgcn.cs.chain(ptr, i32, <3 x i32> inreg, { i32, ptr addrspace(5), i32, i32 }, i32, ...) noreturn
|
|
|
|
define amdgpu_cs_chain void @chain_call(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
|
|
; GFX11-LABEL: name: chain_call
|
|
; GFX11: bb.1 (%ir-block.0):
|
|
; GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
|
|
; GFX11-NEXT: {{ $}}
|
|
; GFX11-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
|
|
; GFX11-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
|
|
; GFX11-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX11-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32)
|
|
; GFX11-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr8
|
|
; GFX11-NEXT: [[COPY4:%[0-9]+]]:_(p5) = COPY $vgpr9
|
|
; GFX11-NEXT: [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr10
|
|
; GFX11-NEXT: [[COPY6:%[0-9]+]]:_(s32) = COPY $vgpr11
|
|
; GFX11-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @callee
|
|
; GFX11-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 -1
|
|
; GFX11-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
|
|
; GFX11-NEXT: [[GV1:%[0-9]+]]:sgpr_64(p0) = G_GLOBAL_VALUE @callee
|
|
; GFX11-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<3 x s32>)
|
|
; GFX11-NEXT: [[INTRINSIC_CONVERGENT:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV]](s32)
|
|
; GFX11-NEXT: $sgpr0 = COPY [[INTRINSIC_CONVERGENT]](s32)
|
|
; GFX11-NEXT: [[INTRINSIC_CONVERGENT1:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV1]](s32)
|
|
; GFX11-NEXT: $sgpr1 = COPY [[INTRINSIC_CONVERGENT1]](s32)
|
|
; GFX11-NEXT: [[INTRINSIC_CONVERGENT2:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV2]](s32)
|
|
; GFX11-NEXT: $sgpr2 = COPY [[INTRINSIC_CONVERGENT2]](s32)
|
|
; GFX11-NEXT: $vgpr8 = COPY [[COPY3]](s32)
|
|
; GFX11-NEXT: $vgpr9 = COPY [[COPY4]](p5)
|
|
; GFX11-NEXT: $vgpr10 = COPY [[COPY5]](s32)
|
|
; GFX11-NEXT: $vgpr11 = COPY [[COPY6]](s32)
|
|
; GFX11-NEXT: SI_CS_CHAIN_TC_W32 [[GV1]](p0), @callee, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
|
|
;
|
|
; GFX10-LABEL: name: chain_call
|
|
; GFX10: bb.1 (%ir-block.0):
|
|
; GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
|
|
; GFX10-NEXT: {{ $}}
|
|
; GFX10-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
|
|
; GFX10-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
|
|
; GFX10-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32)
|
|
; GFX10-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr8
|
|
; GFX10-NEXT: [[COPY4:%[0-9]+]]:_(p5) = COPY $vgpr9
|
|
; GFX10-NEXT: [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr10
|
|
; GFX10-NEXT: [[COPY6:%[0-9]+]]:_(s32) = COPY $vgpr11
|
|
; GFX10-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @callee
|
|
; GFX10-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 -1
|
|
; GFX10-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
|
|
; GFX10-NEXT: [[GV1:%[0-9]+]]:sgpr_64(p0) = G_GLOBAL_VALUE @callee
|
|
; GFX10-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<3 x s32>)
|
|
; GFX10-NEXT: [[INTRINSIC_CONVERGENT:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV]](s32)
|
|
; GFX10-NEXT: $sgpr0 = COPY [[INTRINSIC_CONVERGENT]](s32)
|
|
; GFX10-NEXT: [[INTRINSIC_CONVERGENT1:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV1]](s32)
|
|
; GFX10-NEXT: $sgpr1 = COPY [[INTRINSIC_CONVERGENT1]](s32)
|
|
; GFX10-NEXT: [[INTRINSIC_CONVERGENT2:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV2]](s32)
|
|
; GFX10-NEXT: $sgpr2 = COPY [[INTRINSIC_CONVERGENT2]](s32)
|
|
; GFX10-NEXT: $vgpr8 = COPY [[COPY3]](s32)
|
|
; GFX10-NEXT: $vgpr9 = COPY [[COPY4]](p5)
|
|
; GFX10-NEXT: $vgpr10 = COPY [[COPY5]](s32)
|
|
; GFX10-NEXT: $vgpr11 = COPY [[COPY6]](s32)
|
|
; GFX10-NEXT: [[COPY7:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr48_sgpr49_sgpr50_sgpr51
|
|
; GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]](<4 x s32>)
|
|
; GFX10-NEXT: SI_CS_CHAIN_TC_W32 [[GV1]](p0), @callee, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
|
|
call void(ptr, i32, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee, i32 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
|
|
unreachable
|
|
}
|
|
|
|
define amdgpu_cs_chain void @chain_preserve_call(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
|
|
; GFX11-LABEL: name: chain_preserve_call
|
|
; GFX11: bb.1 (%ir-block.0):
|
|
; GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
|
|
; GFX11-NEXT: {{ $}}
|
|
; GFX11-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
|
|
; GFX11-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
|
|
; GFX11-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX11-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32)
|
|
; GFX11-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr8
|
|
; GFX11-NEXT: [[COPY4:%[0-9]+]]:_(p5) = COPY $vgpr9
|
|
; GFX11-NEXT: [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr10
|
|
; GFX11-NEXT: [[COPY6:%[0-9]+]]:_(s32) = COPY $vgpr11
|
|
; GFX11-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @callee_preserve
|
|
; GFX11-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 -1
|
|
; GFX11-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
|
|
; GFX11-NEXT: [[GV1:%[0-9]+]]:sgpr_64(p0) = G_GLOBAL_VALUE @callee_preserve
|
|
; GFX11-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<3 x s32>)
|
|
; GFX11-NEXT: [[INTRINSIC_CONVERGENT:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV]](s32)
|
|
; GFX11-NEXT: $sgpr0 = COPY [[INTRINSIC_CONVERGENT]](s32)
|
|
; GFX11-NEXT: [[INTRINSIC_CONVERGENT1:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV1]](s32)
|
|
; GFX11-NEXT: $sgpr1 = COPY [[INTRINSIC_CONVERGENT1]](s32)
|
|
; GFX11-NEXT: [[INTRINSIC_CONVERGENT2:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV2]](s32)
|
|
; GFX11-NEXT: $sgpr2 = COPY [[INTRINSIC_CONVERGENT2]](s32)
|
|
; GFX11-NEXT: $vgpr8 = COPY [[COPY3]](s32)
|
|
; GFX11-NEXT: $vgpr9 = COPY [[COPY4]](p5)
|
|
; GFX11-NEXT: $vgpr10 = COPY [[COPY5]](s32)
|
|
; GFX11-NEXT: $vgpr11 = COPY [[COPY6]](s32)
|
|
; GFX11-NEXT: SI_CS_CHAIN_TC_W32 [[GV1]](p0), @callee_preserve, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
|
|
;
|
|
; GFX10-LABEL: name: chain_preserve_call
|
|
; GFX10: bb.1 (%ir-block.0):
|
|
; GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
|
|
; GFX10-NEXT: {{ $}}
|
|
; GFX10-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
|
|
; GFX10-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
|
|
; GFX10-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
|
|
; GFX10-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32)
|
|
; GFX10-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr8
|
|
; GFX10-NEXT: [[COPY4:%[0-9]+]]:_(p5) = COPY $vgpr9
|
|
; GFX10-NEXT: [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr10
|
|
; GFX10-NEXT: [[COPY6:%[0-9]+]]:_(s32) = COPY $vgpr11
|
|
; GFX10-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @callee_preserve
|
|
; GFX10-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 -1
|
|
; GFX10-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
|
|
; GFX10-NEXT: [[GV1:%[0-9]+]]:sgpr_64(p0) = G_GLOBAL_VALUE @callee_preserve
|
|
; GFX10-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<3 x s32>)
|
|
; GFX10-NEXT: [[INTRINSIC_CONVERGENT:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV]](s32)
|
|
; GFX10-NEXT: $sgpr0 = COPY [[INTRINSIC_CONVERGENT]](s32)
|
|
; GFX10-NEXT: [[INTRINSIC_CONVERGENT1:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV1]](s32)
|
|
; GFX10-NEXT: $sgpr1 = COPY [[INTRINSIC_CONVERGENT1]](s32)
|
|
; GFX10-NEXT: [[INTRINSIC_CONVERGENT2:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV2]](s32)
|
|
; GFX10-NEXT: $sgpr2 = COPY [[INTRINSIC_CONVERGENT2]](s32)
|
|
; GFX10-NEXT: $vgpr8 = COPY [[COPY3]](s32)
|
|
; GFX10-NEXT: $vgpr9 = COPY [[COPY4]](p5)
|
|
; GFX10-NEXT: $vgpr10 = COPY [[COPY5]](s32)
|
|
; GFX10-NEXT: $vgpr11 = COPY [[COPY6]](s32)
|
|
; GFX10-NEXT: [[COPY7:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr48_sgpr49_sgpr50_sgpr51
|
|
; GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]](<4 x s32>)
|
|
; GFX10-NEXT: SI_CS_CHAIN_TC_W32 [[GV1]](p0), @callee_preserve, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
|
|
call void(ptr, i32, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee_preserve, i32 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
|
|
unreachable
|
|
}
|
|
|
|
|