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
65 lines
2.8 KiB
LLVM
65 lines
2.8 KiB
LLVM
; RUN: opt %loadNPMPolly '-passes=polly-custom<opt-isl>' -polly-pattern-matching-based-opts=true -debug-only=polly-opt-isl -disable-output -polly-tc-opt=true < %s 2>&1 | FileCheck %s
|
|
; REQUIRES: asserts
|
|
;
|
|
; for (i = 0; i < _PB_NI; i++)
|
|
; for (j = 0; j < _PB_NJ; j++)
|
|
; {
|
|
; for (k = 0; k < _PB_NK; k++)
|
|
; {
|
|
; double Mul = A[i][k] * B[k][j];
|
|
; D[i][j][k] += Mul;
|
|
; C[i][j] += Mul;
|
|
; }
|
|
; }
|
|
;
|
|
; CHECK-NOT: The matrix multiplication pattern was detected
|
|
; CHECK-NOT: The tensor contraction pattern was detected
|
|
|
|
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-linux-gnu"
|
|
|
|
define void @kernel_gemm(ptr %C, ptr %A, ptr %B, ptr %D) {
|
|
entry:
|
|
br label %for.cond1.preheader
|
|
|
|
for.cond1.preheader: ; preds = %for.inc27, %entry
|
|
%indvars.iv7 = phi i64 [ 0, %entry ], [ %indvars.iv.next8, %for.inc27 ]
|
|
br label %for.cond4.preheader
|
|
|
|
for.cond4.preheader: ; preds = %for.inc24, %for.cond1.preheader
|
|
%indvars.iv4 = phi i64 [ 0, %for.cond1.preheader ], [ %indvars.iv.next5, %for.inc24 ]
|
|
%arrayidx22 = getelementptr inbounds [1024 x double], ptr %C, i64 %indvars.iv7, i64 %indvars.iv4
|
|
br label %for.body6
|
|
|
|
for.body6: ; preds = %for.body6, %for.cond4.preheader
|
|
%indvars.iv = phi i64 [ 0, %for.cond4.preheader ], [ %indvars.iv.next, %for.body6 ]
|
|
%arrayidx8 = getelementptr inbounds [1024 x double], ptr %A, i64 %indvars.iv7, i64 %indvars.iv
|
|
%i = load double, ptr %arrayidx8, align 8
|
|
%arrayidx12 = getelementptr inbounds [1024 x double], ptr %B, i64 %indvars.iv, i64 %indvars.iv4
|
|
%i1 = load double, ptr %arrayidx12, align 8
|
|
%mul = fmul double %i1, %i
|
|
%arrayidx18 = getelementptr inbounds [1024 x [1024 x double]], ptr %D, i64 %indvars.iv7, i64 %indvars.iv4, i64 %indvars.iv
|
|
%i2 = load double, ptr %arrayidx18, align 8
|
|
%add = fadd double %i2, %mul
|
|
store double %add, ptr %arrayidx18, align 8
|
|
%i3 = load double, ptr %arrayidx22, align 8
|
|
%add23 = fadd double %i3, %mul
|
|
store double %add23, ptr %arrayidx22, align 8
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond.not = icmp eq i64 %indvars.iv.next, 1024
|
|
br i1 %exitcond.not, label %for.inc24, label %for.body6
|
|
|
|
for.inc24: ; preds = %for.body6
|
|
%indvars.iv.next5 = add nuw nsw i64 %indvars.iv4, 1
|
|
%exitcond6.not = icmp eq i64 %indvars.iv.next5, 1024
|
|
br i1 %exitcond6.not, label %for.inc27, label %for.cond4.preheader
|
|
|
|
for.inc27: ; preds = %for.inc24
|
|
%indvars.iv.next8 = add nuw nsw i64 %indvars.iv7, 1
|
|
%exitcond9.not = icmp eq i64 %indvars.iv.next8, 1024
|
|
br i1 %exitcond9.not, label %for.end29, label %for.cond1.preheader
|
|
|
|
for.end29: ; preds = %for.inc27
|
|
ret void
|
|
}
|