maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/polly/test/GPGPU/simple-managed-memory-rewri...

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

74 lines
2.5 KiB
LLVM
Raw Normal View History

[ManagedMemoryRewrite] Learn how to rewrite global arrays, allocas. - If we have global arrays, we would like to rewrite them to global pointers which are allocated using `cudaMallocManaged`. - If we have allocas in a function, we would like to rewrite them to heap-allocations with `cudaMallocManaged` and `cudaFree`. - With these rewrite mechanisms, we can offload _any_ function to the GPU with no code rewrite whatsover. Differential Revision: https://reviews.llvm.org/D36516 llvm-svn: 311080
2017-08-17 19:22:52 +08:00
; RUN: opt %loadPolly -analyze -polly-process-unprofitable \
; RUN: -polly-scops -polly-use-llvm-names < %s | FileCheck %s --check-prefix=SCOP
; RUN: opt %loadPolly -S -polly-process-unprofitable -polly-acc-mincompute=0 \
; RUN: -polly-target=gpu -polly-codegen-ppcg -polly-acc-codegen-managed-memory \
; RUN: -polly-acc-rewrite-managed-memory < %s | FileCheck %s --check-prefix=HOST-IR
; REQUIRES: pollyacc
; SCOP: Function: f
; SCOP-NEXT: Region: %for.body---%for.end
; SCOP-NEXT: Max Loop Depth: 1
; SCOP: i32 MemRef_A[*];
; Check that we generate a constructor call for @A.toptr
[GPGPU] Make test case independent of LLVM names In release builds LLVM may not pass along LLVM names consistently. We make the test cases independent of the LLVM-IR names to avoid spurious test case failures. llvm-svn: 311118
2017-08-18 04:09:02 +08:00
; HOST-IR: @llvm.global_ctors = appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* {{.*}}, i8* bitcast (i32** @A.toptr to i8*) }]
[ManagedMemoryRewrite] Learn how to rewrite global arrays, allocas. - If we have global arrays, we would like to rewrite them to global pointers which are allocated using `cudaMallocManaged`. - If we have allocas in a function, we would like to rewrite them to heap-allocations with `cudaMallocManaged` and `cudaFree`. - With these rewrite mechanisms, we can offload _any_ function to the GPU with no code rewrite whatsover. Differential Revision: https://reviews.llvm.org/D36516 llvm-svn: 311080
2017-08-17 19:22:52 +08:00
; Check that we generate a constructor
; 4 bytes * 100 = 400
[GPGPU] Make test case independent of LLVM names In release builds LLVM may not pass along LLVM names consistently. We make the test cases independent of the LLVM-IR names to avoid spurious test case failures. llvm-svn: 311118
2017-08-18 04:09:02 +08:00
; HOST-IR: define void {{.*}}constructor() {
[ManagedMemoryRewrite] Learn how to rewrite global arrays, allocas. - If we have global arrays, we would like to rewrite them to global pointers which are allocated using `cudaMallocManaged`. - If we have allocas in a function, we would like to rewrite them to heap-allocations with `cudaMallocManaged` and `cudaFree`. - With these rewrite mechanisms, we can offload _any_ function to the GPU with no code rewrite whatsover. Differential Revision: https://reviews.llvm.org/D36516 llvm-svn: 311080
2017-08-17 19:22:52 +08:00
; HOST-IR-NEXT: entry:
; HOST-IR-NEXT: %mem.raw = call i8* @polly_mallocManaged(i64 400)
; HOST-IR-NEXT: %mem.typed = bitcast i8* %mem.raw to i32*
; HOST-IR-NEXT: store i32* %mem.typed, i32** @A.toptr
; HOST-IR-NEXT: ret void
; HOST-IR-NEXT: }
; HOST-IR-NOT: @A
source_filename = "test.c"
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.12.0"
@A = internal global [100 x i32] zeroinitializer, align 16
define void @f() {
entry:
br label %entry.split
entry.split: ; preds = %entry
br label %for.body
for.body: ; preds = %entry.split, %for.body
%indvars.iv1 = phi i64 [ 0, %entry.split ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds [100 x i32], [100 x i32]* @A, i64 0, i64 %indvars.iv1
store i32 42, i32* %arrayidx, align 4, !tbaa !3
%indvars.iv.next = add nuw nsw i64 %indvars.iv1, 1
%exitcond = icmp eq i64 %indvars.iv.next, 100
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
; Function Attrs: argmemonly nounwind
declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) #0
; Function Attrs: argmemonly nounwind
declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) #0
attributes #0 = { argmemonly nounwind }
!llvm.module.flags = !{!0, !1}
!llvm.ident = !{!2}
!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{i32 7, !"PIC Level", i32 2}
Remove irrelevant references to legacy git repositories from compiler identification lines in test-cases. (Doing so only because it's then easier to search for references which are actually important and need fixing.) llvm-svn: 351200
2019-01-16 00:18:52 +08:00
!2 = !{!"clang version 6.0.0"}
[ManagedMemoryRewrite] Learn how to rewrite global arrays, allocas. - If we have global arrays, we would like to rewrite them to global pointers which are allocated using `cudaMallocManaged`. - If we have allocas in a function, we would like to rewrite them to heap-allocations with `cudaMallocManaged` and `cudaFree`. - With these rewrite mechanisms, we can offload _any_ function to the GPU with no code rewrite whatsover. Differential Revision: https://reviews.llvm.org/D36516 llvm-svn: 311080
2017-08-17 19:22:52 +08:00
!3 = !{!4, !4, i64 0}
!4 = !{!"int", !5, i64 0}
!5 = !{!"omnipotent char", !6, i64 0}
!6 = !{!"Simple C/C++ TBAA"}