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
55 lines
2.8 KiB
LLVM
55 lines
2.8 KiB
LLVM
; RUN: opt %loadNPMPolly '-passes=polly-custom<import-jscop;opt-isl>' -polly-import-jscop-postfix=transformed -polly-pattern-matching-based-opts=true -polly-target-throughput-vector-fma=1 -polly-target-latency-vector-fma=8 -polly-target-1st-cache-level-associativity=8 -polly-target-2nd-cache-level-associativity=8 -polly-target-1st-cache-level-size=32768 -polly-target-vector-register-bitwidth=256 -polly-target-2nd-cache-level-size=262144 -debug -polly-tc-opt=true -disable-output < %s 2>&1 | FileCheck %s
|
|
; REQUIRES: asserts
|
|
;
|
|
; Check that the pattern matching detects the matrix multiplication pattern
|
|
; in case scalar memory accesses were replaced by accesses to newly created
|
|
; arrays.
|
|
;
|
|
; CHECK: The tensor contraction pattern was detected
|
|
; CHECK: The matrix multiplication pattern was detected
|
|
;
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-unknown"
|
|
|
|
define void @kernel_gemm(i32 %ni, i32 %nj, i32 %nk, double %A, ptr %B, ptr %C) {
|
|
entry:
|
|
br label %entry.split
|
|
|
|
entry.split: ; preds = %entry
|
|
br label %for.cond1.preheader
|
|
|
|
for.cond1.preheader: ; preds = %for.inc16, %entry.split
|
|
%indvars.iv35 = phi i64 [ 0, %entry.split ], [ %indvars.iv.next36, %for.inc16 ]
|
|
br label %for.cond4.preheader
|
|
|
|
for.cond4.preheader: ; preds = %for.inc13, %for.cond1.preheader
|
|
%indvars.iv32 = phi i64 [ 0, %for.cond1.preheader ], [ %indvars.iv.next33, %for.inc13 ]
|
|
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 %B, i64 %indvars.iv, i64 %indvars.iv32
|
|
%tmp = load double, ptr %arrayidx8, align 8
|
|
%mul = fmul double %tmp, %A
|
|
%arrayidx12 = getelementptr inbounds [1024 x double], ptr %C, i64 %indvars.iv35, i64 %indvars.iv32
|
|
%tmp1 = load double, ptr %arrayidx12, align 8
|
|
%add = fadd double %tmp1, %mul
|
|
store double %add, ptr %arrayidx12, align 8
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp ne i64 %indvars.iv.next, 1024
|
|
br i1 %exitcond, label %for.body6, label %for.inc13
|
|
|
|
for.inc13: ; preds = %for.body6
|
|
%indvars.iv.next33 = add nuw nsw i64 %indvars.iv32, 1
|
|
%exitcond34 = icmp ne i64 %indvars.iv.next33, 1024
|
|
br i1 %exitcond34, label %for.cond4.preheader, label %for.inc16
|
|
|
|
for.inc16: ; preds = %for.inc13
|
|
%indvars.iv.next36 = add nuw nsw i64 %indvars.iv35, 1
|
|
%exitcond37 = icmp ne i64 %indvars.iv.next36, 1024
|
|
br i1 %exitcond37, label %for.cond1.preheader, label %for.end18
|
|
|
|
for.end18: ; preds = %for.inc16
|
|
ret void
|
|
}
|