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
84 lines
1.9 KiB
LLVM
84 lines
1.9 KiB
LLVM
; REQUIRES: amdgpu-registered-target && x86-registered-target
|
|
; RUN: opt < %s -mtriple=amdgcn -passes=jump-threading -S | FileCheck %s -check-prefixes=CHECK,DIVERGENT
|
|
; RUN: opt < %s -mtriple=x86_64 -passes=jump-threading -S | FileCheck %s -check-prefixes=CHECK,UNIFORM
|
|
|
|
; Here we assure that for the target with no branch divergence usual Jump Threading optimization performed
|
|
; For target with branch divergence - no optimization, so the IR is unchanged.
|
|
|
|
declare i32 @f1()
|
|
declare i32 @f2()
|
|
declare void @f3()
|
|
|
|
define i32 @test(i1 %cond) {
|
|
; CHECK: test
|
|
br i1 %cond, label %T1, label %F1
|
|
|
|
; DIVERGENT: T1
|
|
; UNIFORM-NOT: T1
|
|
T1:
|
|
%v1 = call i32 @f1()
|
|
br label %Merge
|
|
; DIVERGENT: F1
|
|
; UNIFORM-NOT: F1
|
|
F1:
|
|
%v2 = call i32 @f2()
|
|
br label %Merge
|
|
; DIVERGENT: Merge
|
|
; UNIFORM-NOT: Merge
|
|
Merge:
|
|
%A = phi i1 [true, %T1], [false, %F1]
|
|
%B = phi i32 [%v1, %T1], [%v2, %F1]
|
|
br i1 %A, label %T2, label %F2
|
|
|
|
; DIVERGENT: T2
|
|
T2:
|
|
; UNIFORM: T2:
|
|
; UNIFORM: %v1 = call i32 @f1()
|
|
; UNIFORM: call void @f3()
|
|
; UNIFORM: ret i32 %v1
|
|
call void @f3()
|
|
ret i32 %B
|
|
; DIVERGENT: F2
|
|
F2:
|
|
; UNIFORM: F2:
|
|
; UNIFORM: %v2 = call i32 @f2()
|
|
; UNIFORM: ret i32 %v2
|
|
ret i32 %B
|
|
}
|
|
|
|
; Check divergence check is skipped if there can't be divergence in
|
|
; the function.
|
|
define i32 @requires_single_lane_exec(i1 %cond) #0 {
|
|
; CHECK: requires_single_lane_exec
|
|
br i1 %cond, label %T1, label %F1
|
|
|
|
; CHECK-NOT: T1
|
|
T1:
|
|
%v1 = call i32 @f1()
|
|
br label %Merge
|
|
; CHECK-NOT: F1
|
|
F1:
|
|
%v2 = call i32 @f2()
|
|
br label %Merge
|
|
; CHECK-NOT: Merge
|
|
Merge:
|
|
%A = phi i1 [true, %T1], [false, %F1]
|
|
%B = phi i32 [%v1, %T1], [%v2, %F1]
|
|
br i1 %A, label %T2, label %F2
|
|
|
|
T2:
|
|
; CHECK: T2:
|
|
; CHECK: %v1 = call i32 @f1()
|
|
; CHECK: call void @f3()
|
|
; CHECK: ret i32 %v1
|
|
call void @f3()
|
|
ret i32 %B
|
|
F2:
|
|
; CHECK: F2:
|
|
; CHECK: %v2 = call i32 @f2()
|
|
; CHECK: ret i32 %v2
|
|
ret i32 %B
|
|
}
|
|
|
|
attributes #0 = { "amdgpu-flat-work-group-size"="1,1" "amdgpu-no-wwm" }
|