mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-26 12:43:36 +01:00
7e3cf64ceb
Summary: LAA currently generates a set of SCEV predicates that must be checked by users. In the case of Loop Distribute/Loop Load Elimination, no such predicates could have been emitted, since we don't allow stride versioning. However, in the future there could be SCEV predicates that will need to be checked. This change adds support for SCEV predicate versioning in the Loop Distribute, Loop Load Eliminate and the loop versioning infrastructure. Reviewers: anemet Subscribers: mssimpso, sanjoy, llvm-commits Differential Revision: http://reviews.llvm.org/D14240 llvm-svn: 252467
48 lines
1.5 KiB
LLVM
48 lines
1.5 KiB
LLVM
; RUN: opt -loop-load-elim -S < %s | FileCheck %s
|
|
|
|
; Simple st->ld forwarding derived from a lexical forwrad dep.
|
|
;
|
|
; for (unsigned i = 0; i < 100; i++) {
|
|
; A[i+1] = B[i] + 2;
|
|
; C[i] = A[i] * 2;
|
|
; }
|
|
|
|
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
|
|
|
|
define void @f(i32* %A, i32* %B, i32* %C, i64 %N) {
|
|
|
|
; CHECK: for.body.lver.check:
|
|
; CHECK: %found.conflict{{.*}} =
|
|
; CHECK-NOT: %found.conflict{{.*}} =
|
|
|
|
entry:
|
|
; for.body.ph:
|
|
; CHECK: %load_initial = load i32, i32* %A
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
; CHECK: %store_forwarded = phi i32 [ %load_initial, %for.body.ph ], [ %a_p1, %for.body ]
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
|
|
%Aidx_next = getelementptr inbounds i32, i32* %A, i64 %indvars.iv.next
|
|
%Bidx = getelementptr inbounds i32, i32* %B, i64 %indvars.iv
|
|
%Cidx = getelementptr inbounds i32, i32* %C, i64 %indvars.iv
|
|
%Aidx = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
|
|
|
|
%b = load i32, i32* %Bidx, align 4
|
|
%a_p1 = add i32 %b, 2
|
|
store i32 %a_p1, i32* %Aidx_next, align 4
|
|
|
|
%a = load i32, i32* %Aidx, align 4
|
|
; CHECK: %c = mul i32 %store_forwarded, 2
|
|
%c = mul i32 %a, 2
|
|
store i32 %c, i32* %Cidx, align 4
|
|
|
|
%exitcond = icmp eq i64 %indvars.iv.next, %N
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|