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
118 lines
3.6 KiB
LLVM
118 lines
3.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
; NOTE: llvm.amdgcn.wwm is deprecated, use llvm.amdgcn.strict.wwm instead.
|
|
|
|
define amdgpu_hs void @wwm(i32 inreg %arg, ptr addrspace(8) inreg %buffer) {
|
|
; GCN-LABEL: wwm:
|
|
; GCN: ; %bb.0: ; %entry
|
|
; GCN-NEXT: s_mov_b32 s7, s4
|
|
; GCN-NEXT: s_mov_b32 s4, s1
|
|
; GCN-NEXT: s_mov_b32 s1, 16
|
|
; GCN-NEXT: s_mov_b32 s6, s3
|
|
; GCN-NEXT: s_mov_b32 s5, s2
|
|
; GCN-NEXT: v_mov_b32_e32 v0, s1
|
|
; GCN-NEXT: s_cmp_lg_u32 s0, 0
|
|
; GCN-NEXT: s_mov_b32 s0, 0
|
|
; GCN-NEXT: s_cbranch_scc1 .LBB0_2
|
|
; GCN-NEXT: ; %bb.1:
|
|
; GCN-NEXT: s_mov_b32 s0, 1
|
|
; GCN-NEXT: .LBB0_2: ; %bb602
|
|
; GCN-NEXT: v_cmp_eq_u32_e32 vcc, s0, v0
|
|
; GCN-NEXT: s_and_saveexec_b64 s[0:1], vcc
|
|
; GCN-NEXT: s_cbranch_execz .LBB0_4
|
|
; GCN-NEXT: ; %bb.3: ; %bb49
|
|
; GCN-NEXT: v_mov_b32_e32 v0, 1.0
|
|
; GCN-NEXT: tbuffer_store_format_x v0, off, s[4:7], 1 format:[BUF_DATA_FORMAT_32,BUF_NUM_FORMAT_FLOAT] offset:4 glc
|
|
; GCN-NEXT: .LBB0_4: ; %UnifiedReturnBlock
|
|
; GCN-NEXT: s_endpgm
|
|
entry:
|
|
br label %work
|
|
|
|
bb42:
|
|
br label %bb602
|
|
|
|
bb602:
|
|
%tmp603 = phi i32 [ 0, %bb42 ], [ 1, %work ]
|
|
%tmp607 = icmp eq i32 %tmp603, %tmp1196
|
|
br i1 %tmp607, label %bb49, label %bb54
|
|
|
|
bb49:
|
|
call void @llvm.amdgcn.raw.ptr.tbuffer.store.f32(float 1.0, ptr addrspace(8) %buffer, i32 4, i32 1, i32 116, i32 1)
|
|
ret void
|
|
|
|
bb54:
|
|
ret void
|
|
|
|
work:
|
|
%tmp1189 = tail call i32 @llvm.amdgcn.set.inactive.i32(i32 4, i32 1)
|
|
|
|
%tmp1191 = mul i32 %tmp1189, 4
|
|
|
|
%tmp1196 = tail call i32 @llvm.amdgcn.wwm.i32(i32 %tmp1191)
|
|
|
|
%tmp34 = icmp eq i32 %arg, 0
|
|
br i1 %tmp34, label %bb602, label %bb42
|
|
}
|
|
|
|
define amdgpu_hs void @strict_wwm(i32 inreg %arg, ptr addrspace(8) inreg %buffer) {
|
|
; GCN-LABEL: strict_wwm:
|
|
; GCN: ; %bb.0: ; %entry
|
|
; GCN-NEXT: s_mov_b32 s7, s4
|
|
; GCN-NEXT: s_mov_b32 s4, s1
|
|
; GCN-NEXT: s_mov_b32 s1, 16
|
|
; GCN-NEXT: s_mov_b32 s6, s3
|
|
; GCN-NEXT: s_mov_b32 s5, s2
|
|
; GCN-NEXT: v_mov_b32_e32 v0, s1
|
|
; GCN-NEXT: s_cmp_lg_u32 s0, 0
|
|
; GCN-NEXT: s_mov_b32 s0, 0
|
|
; GCN-NEXT: s_cbranch_scc1 .LBB1_2
|
|
; GCN-NEXT: ; %bb.1:
|
|
; GCN-NEXT: s_mov_b32 s0, 1
|
|
; GCN-NEXT: .LBB1_2: ; %bb602
|
|
; GCN-NEXT: v_cmp_eq_u32_e32 vcc, s0, v0
|
|
; GCN-NEXT: s_and_saveexec_b64 s[0:1], vcc
|
|
; GCN-NEXT: s_cbranch_execz .LBB1_4
|
|
; GCN-NEXT: ; %bb.3: ; %bb49
|
|
; GCN-NEXT: v_mov_b32_e32 v0, 1.0
|
|
; GCN-NEXT: tbuffer_store_format_x v0, off, s[4:7], 1 format:[BUF_DATA_FORMAT_32,BUF_NUM_FORMAT_FLOAT] offset:4 glc
|
|
; GCN-NEXT: .LBB1_4: ; %UnifiedReturnBlock
|
|
; GCN-NEXT: s_endpgm
|
|
entry:
|
|
br label %work
|
|
|
|
bb42:
|
|
br label %bb602
|
|
|
|
bb602:
|
|
%tmp603 = phi i32 [ 0, %bb42 ], [ 1, %work ]
|
|
%tmp607 = icmp eq i32 %tmp603, %tmp1196
|
|
br i1 %tmp607, label %bb49, label %bb54
|
|
|
|
bb49:
|
|
call void @llvm.amdgcn.raw.ptr.tbuffer.store.f32(float 1.0, ptr addrspace(8) %buffer, i32 4, i32 1, i32 116, i32 1)
|
|
ret void
|
|
|
|
bb54:
|
|
ret void
|
|
|
|
work:
|
|
%tmp1189 = tail call i32 @llvm.amdgcn.set.inactive.i32(i32 4, i32 1)
|
|
|
|
%tmp1191 = mul i32 %tmp1189, 4
|
|
|
|
%tmp1196 = tail call i32 @llvm.amdgcn.strict.wwm.i32(i32 %tmp1191)
|
|
|
|
%tmp34 = icmp eq i32 %arg, 0
|
|
br i1 %tmp34, label %bb602, label %bb42
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.set.inactive.i32(i32, i32) #0
|
|
declare i32 @llvm.amdgcn.wwm.i32(i32) #1
|
|
declare i32 @llvm.amdgcn.strict.wwm.i32(i32) #1
|
|
declare void @llvm.amdgcn.raw.ptr.tbuffer.store.f32(float, ptr addrspace(8), i32, i32, i32 immarg, i32 immarg) #2
|
|
|
|
attributes #0 = { convergent nounwind readnone willreturn }
|
|
attributes #1 = { convergent nounwind readnone speculatable willreturn }
|
|
attributes #2 = { nounwind willreturn memory(argmem: write) }
|