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

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

diff --git a/lib/Transforms/Vectorize/LoopVectorize.cpp b/lib/Transforms/Vectorize/LoopVectorize.cpp
index 487a7fb..28edd65 100644 (file)
--- a/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -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.

diff --git a/test/Transforms/LoopVectorize/X86/reg-usage.ll b/test/Transforms/LoopVectorize/X86/reg-usage.ll
index 83974d2..9b276aa 100644 (file)
--- a/test/Transforms/LoopVectorize/X86/reg-usage.ll
+++ b/test/Transforms/LoopVectorize/X86/reg-usage.ll
@@ -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