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
59 lines
2.1 KiB
LLVM
59 lines
2.1 KiB
LLVM
; RUN: opt -passes=loop-unroll -S -mtriple=amdgcn-- -mcpu=tahiti %s | FileCheck %s
|
|
|
|
; This IR comes from this OpenCL C code:
|
|
;
|
|
; if (b + 4 > a) {
|
|
; for (int i = 0; i < 4; i++, b++) {
|
|
; if (b + 1 <= a)
|
|
; *(dst + c + b) = 0;
|
|
; else
|
|
; break;
|
|
; }
|
|
; }
|
|
;
|
|
; This test is meant to check that this loop isn't unrolled into more than
|
|
; four iterations. The loop unrolling preferences we currently use cause this
|
|
; loop to not be unrolled at all, but that may change in the future.
|
|
|
|
; CHECK-LABEL: @test
|
|
; CHECK: store i8 0, ptr addrspace(1)
|
|
; CHECK-NOT: store i8 0, ptr addrspace(1)
|
|
; CHECK: ret void
|
|
define amdgpu_kernel void @test(ptr addrspace(1) nocapture %dst, i32 %a, i32 %b, i32 %c) {
|
|
entry:
|
|
%add = add nsw i32 %b, 4
|
|
%cmp = icmp sgt i32 %add, %a
|
|
br i1 %cmp, label %for.cond.preheader, label %if.end7
|
|
|
|
for.cond.preheader: ; preds = %entry
|
|
%cmp313 = icmp slt i32 %b, %a
|
|
br i1 %cmp313, label %if.then4.lr.ph, label %if.end7.loopexit
|
|
|
|
if.then4.lr.ph: ; preds = %for.cond.preheader
|
|
%0 = sext i32 %c to i64
|
|
br label %if.then4
|
|
|
|
if.then4: ; preds = %if.then4.lr.ph, %if.then4
|
|
%i.015 = phi i32 [ 0, %if.then4.lr.ph ], [ %inc, %if.then4 ]
|
|
%b.addr.014 = phi i32 [ %b, %if.then4.lr.ph ], [ %add2, %if.then4 ]
|
|
%add2 = add nsw i32 %b.addr.014, 1
|
|
%1 = sext i32 %b.addr.014 to i64
|
|
%add.ptr.sum = add nsw i64 %1, %0
|
|
%add.ptr5 = getelementptr inbounds i8, ptr addrspace(1) %dst, i64 %add.ptr.sum
|
|
store i8 0, ptr addrspace(1) %add.ptr5, align 1
|
|
%inc = add nsw i32 %i.015, 1
|
|
%cmp1 = icmp slt i32 %inc, 4
|
|
%cmp3 = icmp slt i32 %add2, %a
|
|
%or.cond = and i1 %cmp3, %cmp1
|
|
br i1 %or.cond, label %if.then4, label %for.cond.if.end7.loopexit_crit_edge
|
|
|
|
for.cond.if.end7.loopexit_crit_edge: ; preds = %if.then4
|
|
br label %if.end7.loopexit
|
|
|
|
if.end7.loopexit: ; preds = %for.cond.if.end7.loopexit_crit_edge, %for.cond.preheader
|
|
br label %if.end7
|
|
|
|
if.end7: ; preds = %if.end7.loopexit, %entry
|
|
ret void
|
|
}
|