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
99 lines
4.4 KiB
LLVM
99 lines
4.4 KiB
LLVM
; RUN: opt -S %loadNPMPolly -aa-pipeline=basic-aa -polly-pattern-matching-based-opts=false -polly-vectorizer=stripmine '-passes=polly-custom<opt-isl;ast>' -polly-print-ast -disable-output < %s | FileCheck %s
|
|
; RUN: opt -S %loadNPMPolly -aa-pipeline=basic-aa -polly-pattern-matching-based-opts=false -polly-vectorizer=stripmine -polly-prevect-width=16 '-passes=polly-custom<opt-isl;ast>' -polly-print-ast -disable-output < %s | FileCheck %s -check-prefix=VEC16
|
|
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
|
|
@C = common global [1536 x [1536 x float]] zeroinitializer, align 16
|
|
@A = common global [1536 x [1536 x float]] zeroinitializer, align 16
|
|
@B = common global [1536 x [1536 x float]] zeroinitializer, align 16
|
|
|
|
; Function Attrs: nounwind uwtable
|
|
define void @foo() {
|
|
entry:
|
|
br label %entry.split
|
|
|
|
entry.split: ; preds = %entry
|
|
br label %for.cond1.preheader
|
|
|
|
for.cond1.preheader: ; preds = %entry.split, %for.inc28
|
|
%indvar4 = phi i64 [ 0, %entry.split ], [ %indvar.next5, %for.inc28 ]
|
|
br label %for.body3
|
|
|
|
for.body3: ; preds = %for.cond1.preheader, %for.inc25
|
|
%indvar6 = phi i64 [ 0, %for.cond1.preheader ], [ %indvar.next7, %for.inc25 ]
|
|
%arrayidx24 = getelementptr [1536 x [1536 x float]], ptr @C, i64 0, i64 %indvar4, i64 %indvar6
|
|
store float 0.000000e+00, ptr %arrayidx24, align 4
|
|
br label %for.body8
|
|
|
|
for.body8: ; preds = %for.body3, %for.body8
|
|
%indvar = phi i64 [ 0, %for.body3 ], [ %indvar.next, %for.body8 ]
|
|
%arrayidx16 = getelementptr [1536 x [1536 x float]], ptr @A, i64 0, i64 %indvar4, i64 %indvar
|
|
%arrayidx20 = getelementptr [1536 x [1536 x float]], ptr @B, i64 0, i64 %indvar, i64 %indvar6
|
|
%0 = load float, ptr %arrayidx24, align 4
|
|
%1 = load float, ptr %arrayidx16, align 4
|
|
%2 = load float, ptr %arrayidx20, align 4
|
|
%mul = fmul float %1, %2
|
|
%add = fadd float %0, %mul
|
|
store float %add, ptr %arrayidx24, align 4
|
|
%indvar.next = add i64 %indvar, 1
|
|
%exitcond = icmp ne i64 %indvar.next, 1536
|
|
br i1 %exitcond, label %for.body8, label %for.inc25
|
|
|
|
for.inc25: ; preds = %for.body8
|
|
%indvar.next7 = add i64 %indvar6, 1
|
|
%exitcond8 = icmp ne i64 %indvar.next7, 1536
|
|
br i1 %exitcond8, label %for.body3, label %for.inc28
|
|
|
|
for.inc28: ; preds = %for.inc25
|
|
%indvar.next5 = add i64 %indvar4, 1
|
|
%exitcond9 = icmp ne i64 %indvar.next5, 1536
|
|
br i1 %exitcond9, label %for.cond1.preheader, label %for.end30
|
|
|
|
for.end30: ; preds = %for.inc28
|
|
ret void
|
|
}
|
|
|
|
; CHECK: #pragma known-parallel
|
|
; CHECK: for (int c0 = 0; c0 <= 47; c0 += 1)
|
|
; CHECK: for (int c1 = 0; c1 <= 47; c1 += 1)
|
|
; CHECK: for (int c2 = 0; c2 <= 31; c2 += 1)
|
|
; CHECK: for (int c3 = 0; c3 <= 7; c3 += 1)
|
|
; CHECK: // SIMD
|
|
; CHECK: for (int c4 = 0; c4 <= 3; c4 += 1)
|
|
; CHECK: Stmt_for_body3(32 * c0 + c2, 32 * c1 + 4 * c3 + c4);
|
|
; CHECK: #pragma known-parallel
|
|
; CHECK: for (int c0 = 0; c0 <= 47; c0 += 1)
|
|
; CHECK: for (int c1 = 0; c1 <= 47; c1 += 1)
|
|
; CHECK: for (int c2 = 0; c2 <= 47; c2 += 1)
|
|
; CHECK: for (int c3 = 0; c3 <= 31; c3 += 1)
|
|
; CHECK: for (int c4 = 0; c4 <= 7; c4 += 1)
|
|
; CHECK: for (int c5 = 0; c5 <= 31; c5 += 1)
|
|
; CHECK: // SIMD
|
|
; CHECK: for (int c6 = 0; c6 <= 3; c6 += 1)
|
|
; CHECK: Stmt_for_body8(32 * c0 + c3, 32 * c1 + 4 * c4 + c6, 32 * c2 + c5);
|
|
|
|
; VEC16: {
|
|
; VEC16: #pragma known-parallel
|
|
; VEC16: for (int c0 = 0; c0 <= 47; c0 += 1)
|
|
; VEC16: for (int c1 = 0; c1 <= 47; c1 += 1)
|
|
; VEC16: for (int c2 = 0; c2 <= 31; c2 += 1)
|
|
; VEC16: for (int c3 = 0; c3 <= 1; c3 += 1)
|
|
; VEC16: // SIMD
|
|
; VEC16: for (int c4 = 0; c4 <= 15; c4 += 1)
|
|
; VEC16: Stmt_for_body3(32 * c0 + c2, 32 * c1 + 16 * c3 + c4);
|
|
; VEC16: #pragma known-parallel
|
|
; VEC16: for (int c0 = 0; c0 <= 47; c0 += 1)
|
|
; VEC16: for (int c1 = 0; c1 <= 47; c1 += 1)
|
|
; VEC16: for (int c2 = 0; c2 <= 47; c2 += 1)
|
|
; VEC16: for (int c3 = 0; c3 <= 31; c3 += 1)
|
|
; VEC16: for (int c4 = 0; c4 <= 1; c4 += 1)
|
|
; VEC16: for (int c5 = 0; c5 <= 31; c5 += 1)
|
|
; VEC16: // SIMD
|
|
; VEC16: for (int c6 = 0; c6 <= 15; c6 += 1)
|
|
; VEC16: Stmt_for_body8(32 * c0 + c3, 32 * c1 + 16 * c4 + c6, 32 * c2 + c5);
|
|
; VEC16: }
|
|
|
|
!llvm.ident = !{!0}
|
|
|
|
!0 = !{!"clang version 3.5.0 "}
|