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
101 lines
4.5 KiB
LLVM
101 lines
4.5 KiB
LLVM
; RUN: opt %loadNPMPolly -polly-pattern-matching-based-opts=true '-passes=polly-custom<optree;delicm;simplify;opt-isl>' -polly-tc-opt=true -debug -disable-output < %s 2>&1 | FileCheck %s
|
|
; REQUIRES: asserts
|
|
|
|
; Check that the pattern matching detects the matrix multiplication pattern
|
|
; after a full run of -polly-optree and -polly-delicm, where the write access
|
|
; is not through the original memory access, but through a PHI node that was
|
|
; delicmed. This test covers the polybench 2mm and 3mm cases.
|
|
;
|
|
; This test case generates the following schedule, which contains filters:
|
|
;
|
|
; domain: "{ Stmt_for_body8[i0, i1, i2] : 0 <= i0 <= 1599 and
|
|
; 0 <= i1 <= 1799 and
|
|
; 0 <= i2 <= 2199;
|
|
; Stmt_for_body3[i0, i1] : 0 <= i0 <= 1599 and
|
|
; 0 <= i1 <= 1799;
|
|
; Stmt_for_body3_last[i0, i1] : 0 <= i0 <= 1599 and
|
|
; 0 <= i1 <= 1799 }"
|
|
; child:
|
|
; sequence:
|
|
; - filter: "{ Stmt_for_body3[i0, i1] }"
|
|
; child:
|
|
; schedule: "[{ Stmt_for_body3[i0, i1] -> [(i0)] }, { Stmt_for_body3[i0, i1] -> [(i1)] }]"
|
|
; permutable: 1
|
|
; coincident: [ 1, 1 ]
|
|
; - filter: "{ Stmt_for_body3_last[i0, i1] }"
|
|
; child:
|
|
; schedule: "[{ Stmt_for_body3_last[i0, i1] -> [(i0)] }, { Stmt_for_body3_last[i0, i1] -> [(i1)] }]"
|
|
; permutable: 1
|
|
; coincident: [ 1, 1 ]
|
|
; - filter: "{ Stmt_for_body8[i0, i1, i2] }"
|
|
; child:
|
|
; schedule: "[{ Stmt_for_body8[i0, i1, i2] -> [(i0)] },
|
|
; { Stmt_for_body8[i0, i1, i2] -> [(i1)] },
|
|
; { Stmt_for_body8[i0, i1, i2] -> [(i2)] }]"
|
|
; permutable: 1
|
|
; coincident: [ 1, 1, 0 ]
|
|
;
|
|
; 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-linux-gnu"
|
|
|
|
; Function Attrs: norecurse nounwind uwtable
|
|
define void @kernel_2mm(i32 %ni, i32 %nj, i32 %nk, i32 %nl, double %alpha, double %beta, ptr nocapture %tmp, ptr nocapture readonly %A, ptr nocapture readonly %B, ptr nocapture readnone %C, ptr nocapture readnone %D) local_unnamed_addr {
|
|
entry:
|
|
br label %entry.split
|
|
|
|
entry.split: ; preds = %entry
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.inc25, %entry.split
|
|
%indvars.iv50 = phi i64 [ 0, %entry.split ], [ %indvars.iv.next51, %for.inc25 ]
|
|
br label %for.body3
|
|
|
|
for.body3: ; preds = %for.inc22, %for.body
|
|
%indvars.iv46 = phi i64 [ 0, %for.body ], [ %indvars.iv.next47, %for.inc22 ]
|
|
%arrayidx5 = getelementptr inbounds [1800 x double], ptr %tmp, i64 %indvars.iv50, i64 %indvars.iv46
|
|
store double 0.000000e+00, ptr %arrayidx5, align 8, !tbaa !2
|
|
br label %for.body8
|
|
|
|
for.body8: ; preds = %for.body8, %for.body3
|
|
%0 = phi double [ 0.000000e+00, %for.body3 ], [ %add, %for.body8 ]
|
|
%indvars.iv = phi i64 [ 0, %for.body3 ], [ %indvars.iv.next, %for.body8 ]
|
|
%arrayidx12 = getelementptr inbounds [2200 x double], ptr %A, i64 %indvars.iv50, i64 %indvars.iv
|
|
%1 = load double, ptr %arrayidx12, align 8, !tbaa !2
|
|
%mul = fmul double %1, %alpha
|
|
%arrayidx16 = getelementptr inbounds [1800 x double], ptr %B, i64 %indvars.iv, i64 %indvars.iv46
|
|
%2 = load double, ptr %arrayidx16, align 8, !tbaa !2
|
|
%mul17 = fmul double %mul, %2
|
|
%add = fadd double %0, %mul17
|
|
store double %add, ptr %arrayidx5, align 8, !tbaa !2
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp eq i64 %indvars.iv.next, 2200
|
|
br i1 %exitcond, label %for.inc22, label %for.body8
|
|
|
|
for.inc22: ; preds = %for.body8
|
|
%indvars.iv.next47 = add nuw nsw i64 %indvars.iv46, 1
|
|
%exitcond48 = icmp eq i64 %indvars.iv.next47, 1800
|
|
br i1 %exitcond48, label %for.inc25, label %for.body3
|
|
|
|
for.inc25: ; preds = %for.inc22
|
|
%indvars.iv.next51 = add nuw nsw i64 %indvars.iv50, 1
|
|
%exitcond52 = icmp eq i64 %indvars.iv.next51, 1600
|
|
br i1 %exitcond52, label %for.end27, label %for.body
|
|
|
|
for.end27: ; preds = %for.inc25
|
|
ret void
|
|
}
|
|
|
|
!llvm.module.flags = !{!0}
|
|
!llvm.ident = !{!1}
|
|
|
|
!0 = !{i32 1, !"wchar_size", i32 4}
|
|
!1 = !{!"clang version 6.0.0 (trunk 309912) (llvm/trunk 309933)"}
|
|
!2 = !{!3, !3, i64 0}
|
|
!3 = !{!"double", !4, i64 0}
|
|
!4 = !{!"omnipotent char", !5, i64 0}
|
|
!5 = !{!"Simple C/C++ TBAA"}
|