RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2025-01-09 05:31:37 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[LV] Avoid computing the register usage for default VF. NFC

Browse Source 
These are changes to reduce redundant computations when calculating a
feasible vectorization factor:
1. early return when target has no vector registers
2. don't compute register usage for the default VF.

Suggested during review for D37702.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@313176 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Anna Thomas 2017-09-13 19:35:45 +00:00
parent 65bdf0ae4a
commit fb0da33fc1
2 changed files with 4 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -6241,6 +6241,7 @@ LoopVectorizationCostModel::computeFeasibleMaxVF(bool OptForSize,
if (MaxVectorSize == 0) {
DEBUG(dbgs() << "LV: The target has no vector registers.\n");
MaxVectorSize = 1;
return MaxVectorSize;
} else if (ConstTripCount && ConstTripCount < MaxVectorSize &&
isPowerOf2_32(ConstTripCount)) {
// We need to clamp the VF to be the ConstTripCount. There is no point in
@ -6253,10 +6254,11 @@ LoopVectorizationCostModel::computeFeasibleMaxVF(bool OptForSize,
unsigned MaxVF = MaxVectorSize;
if (MaximizeBandwidth && !OptForSize) {
// Collect all viable vectorization factors.
// Collect all viable vectorization factors larger than the default MaxVF
// (i.e. MaxVectorSize).
SmallVector<unsigned, 8> VFs;
unsigned NewMaxVectorSize = WidestRegister / SmallestType;
for (unsigned VS = MaxVectorSize; VS <= NewMaxVectorSize; VS *= 2)
for (unsigned VS = MaxVectorSize * 2; VS <= NewMaxVectorSize; VS *= 2)
VFs.push_back(VS);
// For each VF calculate its register usage.

4
test/Transforms/LoopVectorize/X86/reg-usage.ll
View File

@ -10,8 +10,6 @@ define i32 @foo() {
; register usage doesn't exceed 16.
;
; CHECK-LABEL: foo
; CHECK: LV(REG): VF = 4
; CHECK-NEXT: LV(REG): Found max usage: 4
; CHECK: LV(REG): VF = 8
; CHECK-NEXT: LV(REG): Found max usage: 7
; CHECK: LV(REG): VF = 16
@ -48,8 +46,6 @@ define i32 @goo() {
; it will not have vector version and the vector register usage will not exceed the
; available vector register number.
; CHECK-LABEL: goo
; CHECK: LV(REG): VF = 4
; CHECK-NEXT: LV(REG): Found max usage: 4
; CHECK: LV(REG): VF = 8
; CHECK-NEXT: LV(REG): Found max usage: 7
; CHECK: LV(REG): VF = 16