maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[TTI] `BasicTTIImplBase::getInterleavedMemoryOpCost()`: fix load discounting 

The math here is:
Cost of 1 load = cost of n loads / n
Cost of live loads = num live loads * Cost of 1 load
Cost of live loads = num live loads * (cost of n loads / n)
Cost of live loads = cost of n loads * (num live loads / n)

But, all the variables here are integers,
and integer division rounds down,
but this calculation clearly expects float semantics.

Instead multiply upfront, and then perform round-up-division.

Reviewed By: RKSimon

Differential Revision: https://reviews.llvm.org/D112302
This commit is contained in:
Roman Lebedev 2021-10-22 14:04:38 +03:00
parent 8ae83a1baf
commit 2eaef53023
No known key found for this signature in database
GPG Key ID: 083C3EBB4A1689E0
2 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
llvm/include/llvm/CodeGen/BasicTTIImpl.h
View File

@ -1214,7 +1214,7 @@ public:
//
// TODO: Note that legalization can turn masked loads/stores into unmasked
// (legalized) loads/stores. This can be reflected in the cost.
if (VecTySize > VecTyLTSize) {
if (Cost.isValid() && VecTySize > VecTyLTSize) {
// The number of loads of a legal type it will take to represent a load
// of the unlegalized vector type.
unsigned NumLegalInsts = divideCeil(VecTySize, VecTyLTSize);
@ -1231,7 +1231,8 @@ public:
// Scale the cost of the load by the fraction of legal instructions that
// will be used.
Cost *= UsedInsts.count() / NumLegalInsts;
Cost = divideCeil(UsedInsts.count() * Cost.getValue().getValue(),
NumLegalInsts);
}
// Then plus the cost of interleave operation.

2
llvm/test/Transforms/LoopVectorize/AArch64/interleaved_cost.ll
View File

@ -168,7 +168,7 @@ entry:
; gaps.
;
; VF_2-LABEL: Checking a loop in "i64_factor_8"
; VF_2: Found an estimated cost of 6 for VF 2 For instruction: %tmp2 = load i64, i64* %tmp0, align 8
; VF_2: Found an estimated cost of 10 for VF 2 For instruction: %tmp2 = load i64, i64* %tmp0, align 8
; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load i64, i64* %tmp1, align 8
; VF_2-NEXT: Found an estimated cost of 7 for VF 2 For instruction: store i64 0, i64* %tmp0, align 8
; VF_2-NEXT: Found an estimated cost of 7 for VF 2 For instruction: store i64 0, i64* %tmp1, align 8