bc88a78cb4
The previous algorithm was to search a writes and the sours of its value operand, and see whether the write just stores the same read value back, which includes a search whether there is another write access between them. This is O(n^2) in the max number of accesses in a statement (+ the complexity of isl comparing the access functions). The new algorithm is more similar to the one used for searching for overwrites and coalescable writes. It scans over all accesses in order of execution while tracking which array elements still have the same value since it was read. This is O(n), not counting the complexity within isl. It should be more reliable than trying to catch all non-conforming cases in the previous approach. It is also less code. We now also support if the write is a partial write of the read's domain, and to some extent non-affine subregions. Differential Revision: https://reviews.llvm.org/D36137 llvm-svn: 309734
41 lines
881 B
LLVM
41 lines
881 B
LLVM
; RUN: opt %loadPolly -polly-import-jscop -polly-import-jscop-postfix=transformed -polly-simplify -analyze < %s | FileCheck %s -match-full-lines
|
|
;
|
|
; Remove a redundant store, if its partial domain is a subset of the
|
|
; read's domain.
|
|
;
|
|
define void @redundant_partialwrite(i32 %n, double* noalias nonnull %A) {
|
|
entry:
|
|
br label %for
|
|
|
|
for:
|
|
%j = phi i32 [0, %entry], [%j.inc, %inc]
|
|
%j.cmp = icmp slt i32 %j, %n
|
|
br i1 %j.cmp, label %body, label %exit
|
|
|
|
body:
|
|
%val = load double, double* %A
|
|
store double %val, double* %A
|
|
br label %inc
|
|
|
|
inc:
|
|
%j.inc = add nuw nsw i32 %j, 1
|
|
br label %for
|
|
|
|
exit:
|
|
br label %return
|
|
|
|
return:
|
|
ret void
|
|
}
|
|
|
|
|
|
; Check successful import.
|
|
; CHECK: new: [n] -> { Stmt_body[i0] -> MemRef_A[0] : i0 <= 15 };
|
|
|
|
; CHECK: Statistics {
|
|
; CHECK: Redundant writes removed: 1
|
|
; CHECK: }
|
|
|
|
; CHECK: After accesses {
|
|
; CHECK-NEXT: }
|