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
114 lines
3.6 KiB
LLVM
114 lines
3.6 KiB
LLVM
; RUN: opt < %s -S -mtriple=amdgcn-- -passes=loop-unroll | FileCheck %s
|
|
|
|
; Check the handling of amdgpu.loop.unroll.threshold metadata which can be used to
|
|
; set the default threshold for a loop. This metadata overrides both the AMDGPU
|
|
; default, and any value specified by the amdgpu-unroll-threshold function attribute
|
|
; (which sets a threshold for all loops in the function).
|
|
|
|
; Check that the loop in unroll_default is not fully unrolled using the default
|
|
; unroll threshold
|
|
; CHECK-LABEL: @unroll_default
|
|
; CHECK: entry:
|
|
; CHECK: br i1 %cmp
|
|
; CHECK: ret void
|
|
|
|
@in = internal unnamed_addr global ptr null, align 8
|
|
@out = internal unnamed_addr global ptr null, align 8
|
|
|
|
define void @unroll_default() {
|
|
entry:
|
|
br label %do.body
|
|
|
|
do.body: ; preds = %entry
|
|
%i.0 = phi i32 [ 0, %entry ], [ %inc, %do.body ]
|
|
%v1 = load i64, ptr @in, align 8
|
|
store i64 %v1, ptr @out, align 8
|
|
%inc = add nsw i32 %i.0, 1
|
|
%cmp = icmp slt i32 %inc, 100
|
|
br i1 %cmp, label %do.body, label %do.end
|
|
|
|
do.end: ; preds = %do.body
|
|
ret void
|
|
}
|
|
|
|
; Check that the same loop in unroll_full is fully unrolled when the default
|
|
; unroll threshold is increased by use of the amdgpu.loop.unroll.threshold metadata
|
|
; CHECK-LABEL: @unroll_full
|
|
; CHECK: entry:
|
|
; CHECK-NOT: br i1 %cmp
|
|
; CHECK: ret void
|
|
|
|
define void @unroll_full() {
|
|
entry:
|
|
br label %do.body
|
|
|
|
do.body: ; preds = %entry
|
|
%i.0 = phi i32 [ 0, %entry ], [ %inc, %do.body ]
|
|
%v1 = load i64, ptr @in, align 8
|
|
store i64 %v1, ptr @out, align 8
|
|
%inc = add nsw i32 %i.0, 1
|
|
%cmp = icmp slt i32 %inc, 100
|
|
br i1 %cmp, label %do.body, label %do.end, !llvm.loop !1
|
|
|
|
do.end: ; preds = %do.body
|
|
ret void
|
|
}
|
|
|
|
; Check that the same loop in override_no_unroll is not unrolled when a high default
|
|
; unroll threshold specified using the amdgpu-unroll-threshold function attribute
|
|
; is overridden by a low threshold using the amdgpu.loop.unroll.threshold metadata
|
|
|
|
; CHECK-LABEL: @override_no_unroll
|
|
; CHECK: entry:
|
|
; CHECK: br i1 %cmp
|
|
; CHECK: ret void
|
|
|
|
define void @override_no_unroll() #0 {
|
|
entry:
|
|
br label %do.body
|
|
|
|
do.body: ; preds = %entry
|
|
%i.0 = phi i32 [ 0, %entry ], [ %inc, %do.body ]
|
|
%v1 = load i64, ptr @in, align 8
|
|
store i64 %v1, ptr @out, align 8
|
|
%inc = add nsw i32 %i.0, 1
|
|
%cmp = icmp slt i32 %inc, 100
|
|
br i1 %cmp, label %do.body, label %do.end, !llvm.loop !3
|
|
|
|
do.end: ; preds = %do.body
|
|
ret void
|
|
}
|
|
|
|
; Check that the same loop in override_unroll is fully unrolled when a low default
|
|
; unroll threshold specified using the amdgpu-unroll-threshold function attribute
|
|
; is overridden by a high threshold using the amdgpu.loop.unroll.threshold metadata
|
|
|
|
; CHECK-LABEL: @override_unroll
|
|
; CHECK: entry:
|
|
; CHECK-NOT: br i1 %cmp
|
|
; CHECK: ret void
|
|
|
|
define void @override_unroll() #1 {
|
|
entry:
|
|
br label %do.body
|
|
|
|
do.body: ; preds = %entry
|
|
%i.0 = phi i32 [ 0, %entry ], [ %inc, %do.body ]
|
|
%v1 = load i64, ptr @in, align 8
|
|
store i64 %v1, ptr @out, align 8
|
|
%inc = add nsw i32 %i.0, 1
|
|
%cmp = icmp slt i32 %inc, 100
|
|
br i1 %cmp, label %do.body, label %do.end, !llvm.loop !1
|
|
|
|
do.end: ; preds = %do.body
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { "amdgpu-unroll-threshold"="1000" }
|
|
attributes #1 = { "amdgpu-unroll-threshold"="100" }
|
|
|
|
!1 = !{!1, !2}
|
|
!2 = !{!"amdgpu.loop.unroll.threshold", i32 1000}
|
|
!3 = !{!3, !4}
|
|
!4 = !{!"amdgpu.loop.unroll.threshold", i32 100}
|