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
62 lines
2.2 KiB
LLVM
62 lines
2.2 KiB
LLVM
; RUN: opt %s -passes='print<uniformity>' -disable-output 2>&1 | FileCheck %s
|
|
|
|
; NOTE: The new pass manager does not fall back on legacy divergence
|
|
; analysis even when the function contains an irreducible loop. The
|
|
; (new) divergence analysis conservatively reports all values as
|
|
; divergent. This test does not check for this conservative
|
|
; behaviour. Instead, it only checks for the values that are known to
|
|
; be divergent according to the legacy analysis.
|
|
|
|
target datalayout = "e-i64:64-v16:16-v32:32-n16:32:64"
|
|
target triple = "nvptx64-nvidia-cuda"
|
|
|
|
; This test contains an unstructured loop.
|
|
; +-------------- entry ----------------+
|
|
; | |
|
|
; V V
|
|
; i1 = phi(0, i3) i2 = phi(0, i3)
|
|
; j1 = i1 + 1 ---> i3 = phi(j1, j2) <--- j2 = i2 + 2
|
|
; ^ | ^
|
|
; | V |
|
|
; +-------- switch (tid / i3) ----------+
|
|
; |
|
|
; V
|
|
; if (i3 == 5) // divergent
|
|
; because sync dependent on (tid / i3).
|
|
define ptx_kernel i32 @unstructured_loop(i1 %entry_cond) {
|
|
; CHECK-LABEL: for function 'unstructured_loop'
|
|
entry:
|
|
%tid = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
|
|
br i1 %entry_cond, label %loop_entry_1, label %loop_entry_2
|
|
loop_entry_1:
|
|
%i1 = phi i32 [ 0, %entry ], [ %i3, %loop_latch ]
|
|
%j1 = add i32 %i1, 1
|
|
br label %loop_body
|
|
loop_entry_2:
|
|
%i2 = phi i32 [ 0, %entry ], [ %i3, %loop_latch ]
|
|
%j2 = add i32 %i2, 2
|
|
br label %loop_body
|
|
loop_body:
|
|
%i3 = phi i32 [ %j1, %loop_entry_1 ], [ %j2, %loop_entry_2 ]
|
|
br label %loop_latch
|
|
loop_latch:
|
|
%div = sdiv i32 %tid, %i3
|
|
switch i32 %div, label %branch [ i32 1, label %loop_entry_1
|
|
i32 2, label %loop_entry_2 ]
|
|
branch:
|
|
%cmp = icmp eq i32 %i3, 5
|
|
br i1 %cmp, label %then, label %else
|
|
; CHECK: DIVERGENT: %cmp =
|
|
; CHECK: DIVERGENT: br i1 %cmp,
|
|
then:
|
|
ret i32 0
|
|
else:
|
|
ret i32 1
|
|
}
|
|
|
|
declare i32 @llvm.nvvm.read.ptx.sreg.tid.x()
|
|
declare i32 @llvm.nvvm.read.ptx.sreg.tid.y()
|
|
declare i32 @llvm.nvvm.read.ptx.sreg.tid.z()
|
|
declare i32 @llvm.nvvm.read.ptx.sreg.laneid()
|
|
|