diff options
Diffstat (limited to 'llvm')
| -rw-r--r-- | llvm/lib/Transforms/Vectorize/LoopVectorize.cpp | 24 | ||||
| -rw-r--r-- | llvm/test/Transforms/LoopVectorize/X86/no_fpmath_with_hotness.ll | 2 |
2 files changed, 13 insertions, 13 deletions
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp index e6c481f81ee..44623dd0ebc 100644 --- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp +++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp @@ -200,9 +200,10 @@ static cl::opt<bool> EnableMaskedInterleavedMemAccesses( "enable-masked-interleaved-mem-accesses", cl::init(false), cl::Hidden, cl::desc("Enable vectorization on masked interleaved memory accesses in a loop")); -/// We don't interleave loops with a known constant trip count below this -/// number. -static const unsigned TinyTripCountInterleaveThreshold = 128; +static cl::opt<unsigned> TinyTripCountInterleaveThreshold( + "tiny-trip-count-interleave-threshold", cl::init(128), cl::Hidden, + cl::desc("We don't interleave loops with a estimated constant trip count " + "below this number")); static cl::opt<unsigned> ForceTargetNumScalarRegs( "force-target-num-scalar-regs", cl::init(0), cl::Hidden, @@ -5143,9 +5144,10 @@ unsigned LoopVectorizationCostModel::selectInterleaveCount(unsigned VF, if (Legal->getMaxSafeDepDistBytes() != -1U) return 1; - // Do not interleave loops with a relatively small trip count. - unsigned TC = PSE.getSE()->getSmallConstantTripCount(TheLoop); - if (TC > 1 && TC < TinyTripCountInterleaveThreshold) + // Do not interleave loops with a relatively small known or estimated trip + // count. + auto BestKnownTC = getSmallBestKnownTC(*PSE.getSE(), TheLoop); + if (BestKnownTC && *BestKnownTC < TinyTripCountInterleaveThreshold) return 1; RegisterUsage R = calculateRegisterUsage({VF})[0]; @@ -5208,12 +5210,10 @@ unsigned LoopVectorizationCostModel::selectInterleaveCount(unsigned VF, MaxInterleaveCount = ForceTargetMaxVectorInterleaveFactor; } - // If the trip count is constant, limit the interleave count to be less than - // the trip count divided by VF. - if (TC > 0) { - assert(TC >= VF && "VF exceeds trip count?"); - if ((TC / VF) < MaxInterleaveCount) - MaxInterleaveCount = (TC / VF); + // If trip count is known or estimated compile time constant, limit the + // interleave count to be less than the trip count divided by VF. + if (BestKnownTC) { + MaxInterleaveCount = std::min(*BestKnownTC / VF, MaxInterleaveCount); } // If we did not calculate the cost for VF (because the user selected the VF) diff --git a/llvm/test/Transforms/LoopVectorize/X86/no_fpmath_with_hotness.ll b/llvm/test/Transforms/LoopVectorize/X86/no_fpmath_with_hotness.ll index fbc4ab2aa86..f593b9423e3 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/no_fpmath_with_hotness.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/no_fpmath_with_hotness.ll @@ -3,7 +3,7 @@ ; CHECK: remark: no_fpmath.c:6:11: loop not vectorized: cannot prove it is safe to reorder floating-point operations (hotness: 300) ; CHECK: remark: no_fpmath.c:6:14: loop not vectorized -; CHECK: remark: no_fpmath.c:17:14: vectorized loop (vectorization width: 2, interleaved count: 2) (hotness: 300) +; CHECK: remark: no_fpmath.c:17:14: vectorized loop (vectorization width: 2, interleaved count: 1) (hotness: 300) target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" target triple = "x86_64-apple-macosx10.10.0" |
