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
56 lines
1.8 KiB
LLVM
56 lines
1.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
; optnone disables AMDGPUAnnotateUniformValues, so no branch is known
|
|
; to be uniform during instruction selection. The custom selection for
|
|
; brcond was not checking if the branch was uniform, relying on the
|
|
; selection pattern to check that. That would fail, so then the branch
|
|
; would fail to select.
|
|
|
|
; GCN-LABEL: {{^}}copytoreg_divergent_brcond:
|
|
; GCN: s_branch
|
|
|
|
; GCN-DAG: v_cmp_lt_i32
|
|
; GCN-DAG: s_cmp_gt_i32
|
|
; GCN: s_and_b64
|
|
; GCN: s_mov_b64 exec
|
|
|
|
; GCN: s_or_b64 exec, exec
|
|
; GCN: {{[s|v]}}_cmp_eq_u32
|
|
; GCN: s_cbranch_execz
|
|
; GCN-NEXT: s_branch
|
|
define amdgpu_kernel void @copytoreg_divergent_brcond(i32 %arg, i32 %arg1, i32 %arg2) #0 {
|
|
bb:
|
|
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tmp3 = zext i32 %tmp to i64
|
|
%tmp5 = add i64 %tmp3, undef
|
|
%tmp6 = trunc i64 %tmp5 to i32
|
|
%tmp7 = mul nsw i32 %tmp6, %arg2
|
|
br label %bb8
|
|
|
|
bb8.loopexit: ; preds = %bb14
|
|
br label %bb8
|
|
|
|
bb8: ; preds = %bb8.loopexit, %bb
|
|
br label %bb9
|
|
|
|
bb9: ; preds = %bb14, %bb8
|
|
%tmp10 = icmp slt i32 %tmp7, %arg1
|
|
%tmp11 = icmp sgt i32 %arg, 0
|
|
%tmp12 = and i1 %tmp10, %tmp11
|
|
br i1 %tmp12, label %bb13, label %bb14
|
|
|
|
bb13: ; preds = %bb9
|
|
store volatile i32 0, ptr addrspace(1) poison, align 4
|
|
br label %bb14
|
|
|
|
bb14: ; preds = %bb13, %bb9
|
|
%tmp15 = icmp eq i32 %arg2, 1
|
|
br i1 %tmp15, label %bb8.loopexit, label %bb9
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() #1
|
|
|
|
attributes #0 = { nounwind optnone noinline }
|
|
attributes #1 = { nounwind readnone speculatable }
|