[PATCH] D108763: Use type sizes when determining dependence
Jolanta Jensen via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Mon Sep 27 04:02:13 PDT 2021
jolanta.jensen marked an inline comment as done.
jolanta.jensen added inline comments.
================
Comment at: llvm/test/Transforms/LoopVectorize/depend_diff_types.ll:11
+;
+; subroutine foo(V1,V3,M,N)
+; implicit none
----------------
fhahn wrote:
> Please try to simplify the input IR and try to motivate/explain the problem only based on the input IR.
The whole test is rewritten.
================
Comment at: llvm/test/Transforms/LoopVectorize/depend_diff_types.ll:58-63
+ %20 = add nsw i64 %indvars.iv, -1824
+ %21 = getelementptr i64, i64* %4, i64 %20
+ %22 = load i64, i64* %21, align 8, !tbaa !6
+ %23 = add nuw i64 %indvars.iv, 15296
+ %24 = getelementptr i64, i64* %3, i64 %23
+ store i64 %22, i64* %24, align 8, !tbaa !4
----------------
malharJ wrote:
> perhaps this can be removed ?
>
> It looks like the IR corresponds to
>
>
> ```
> 1) v3[i+31] = (v1[1903+i] * v3[1023+i]); // ---> all accesses are double*
>
> 2) v3[i+1007] = v1[i+47]; // ---> all accesses are i64*
>
> 3) v3[i+16319] = v1[i+79]; // ---> all accesses are i64* (could remove ?)
> ```
>
> Perhaps we are only concerned with the lines 1 and 2, as they are of different types ?
The whole test is rewritten.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D108763/new/
https://reviews.llvm.org/D108763
More information about the llvm-commits
mailing list