6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2026-04-20 16:17:38 +00:00
Code Issues Projects Releases Wiki Activity

LoopVectorizer: When we vectorizer and widen loops we process many elements at once. This is a good thing, except for

Browse Source 
small loops. On small loops post-loop that handles scalars (and runs slower) can take more time to execute than the
rest of the loop. This patch disables widening of loops with a small static trip count.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171798 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Nadav Rotem
2013-01-07 21:54:51 +00:00
parent 6c1d4972cf
commit 9a6c6a3736
2 changed files with 65 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/Transforms/Vectorize/LoopVectorize.cpp
+15 -3
View File
@@ -101,7 +101,13 @@ EnableIfConversion("enable-if-conversion", cl::init(true), cl::Hidden,
cl::desc("Enable if-conversion during vectorization."));
/// We don't vectorize loops with a known constant trip count below this number.
static const unsigned TinyTripCountThreshold = 16;
static const unsigned TinyTripCountVectorThreshold = 16;
/// We don't unroll loops with a known constant trip count below this number.
static const unsigned TinyTripCountUnrollThreshold = 128;
/// We don't unroll loops that are larget than this threshold.
static const unsigned MaxLoopSizeThreshold = 32;
/// When performing a runtime memory check, do not check more than this
/// number of pointers. Notice that the check is quadratic!
@@ -2016,7 +2022,7 @@ bool LoopVectorizationLegality::canVectorize() {
// Do not loop-vectorize loops with a tiny trip count.
unsigned TC = SE->getSmallConstantTripCount(TheLoop, Latch);
if (TC > 0u && TC < TinyTripCountThreshold) {
if (TC > 0u && TC < TinyTripCountVectorThreshold) {
DEBUG(dbgs() << "LV: Found a loop with a very small trip count. " <<
"This loop is not worth vectorizing.\n");
return false;
@@ -2678,6 +2684,12 @@ LoopVectorizationCostModel::selectUnrollFactor(bool OptForSize,
if (OptForSize)
return 1;
// Do not unroll loops with a relatively small trip count.
unsigned TC = SE->getSmallConstantTripCount(TheLoop,
TheLoop->getLoopLatch());
if (TC > 1 && TC < TinyTripCountUnrollThreshold)
return 1;
unsigned TargetVectorRegisters = TTI.getNumberOfRegisters(true);
DEBUG(dbgs() << "LV: The target has " << TargetVectorRegisters <<
" vector registers\n");
@@ -2698,7 +2710,7 @@ LoopVectorizationCostModel::selectUnrollFactor(bool OptForSize,
// We don't want to unroll the loops to the point where they do not fit into
// the decoded cache. Assume that we only allow 32 IR instructions.
UF = std::min(UF, (32 / R.NumInstructions));
UF = std::min(UF, (MaxLoopSizeThreshold / R.NumInstructions));
// Clamp the unroll factor ranges to reasonable factors.
if (UF > MaxUnrollSize)