summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorSanjay Patel <spatel@rotateright.com>2016-03-01 23:55:18 +0000
committerSanjay Patel <spatel@rotateright.com>2016-03-01 23:55:18 +0000
commit147e9279570a5afa297f9b1a7f5ff0b26a05758d (patch)
treebc8153ff050c6bf9026fb5965ecfc48c23a55569
parent947648f5023cb23644cd0071bc958783f74994e4 (diff)
downloadbcm5719-llvm-147e9279570a5afa297f9b1a7f5ff0b26a05758d.tar.gz
bcm5719-llvm-147e9279570a5afa297f9b1a7f5ff0b26a05758d.zip
[InstCombine] convert 'isPositive' and 'isNegative' vector comparisons to shifts (PR26701)
As noted in the code comment, I don't think we can do the same transform that we do for *scalar* integers comparisons to *vector* integers comparisons because it might pessimize the general case. Exhibit A for an incomplete integer comparison ISA remains x86 SSE/AVX: it only has EQ and GT for integer vectors. But we should now recognize all the variants of this construct and produce the optimal code for the cases shown in: https://llvm.org/bugs/show_bug.cgi?id=26701 llvm-svn: 262424
-rw-r--r--llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp22
-rw-r--r--llvm/test/Transforms/InstCombine/vec_sext.ll28
2 files changed, 45 insertions, 5 deletions
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
index 6d0e8821e8f..3cf38c33853 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
@@ -976,16 +976,28 @@ Instruction *InstCombiner::transformSExtICmp(ICmpInst *ICI, Instruction &CI) {
// (x <s 0) ? -1 : 0 -> ashr x, 31 -> all ones if negative
// (x >s -1) ? -1 : 0 -> not (ashr x, 31) -> all ones if positive
if ((Pred == ICmpInst::ICMP_SLT && Op1C->isNullValue()) ||
- (Pred == ICmpInst::ICMP_SGT && Op1C->isAllOnesValue())) {
+ (Pred == ICmpInst::ICMP_SGT && Op1C->isAllOnesValue()) ||
+ // The following patterns should only be present for vectors.
+ // For scalar integers, the comparison should be canonicalized to one of
+ // the above forms. We don't do that for vectors because vector ISAs may
+ // not have a full range of comparison operators. This transform,
+ // however, will simplify the IR, so we always do it.
+ //
+ // (x <=s -1) ? -1 : 0 -> ashr x, 31 -> all ones if negative
+ // (x >=s 0) ? -1 : 0 -> not (ashr x, 31) -> all ones if positive
+ (Pred == ICmpInst::ICMP_SLE && Op1C->isAllOnesValue()) ||
+ (Pred == ICmpInst::ICMP_SGE && Op1C->isNullValue())) {
Value *Sh = ConstantInt::get(Op0->getType(),
- Op0->getType()->getScalarSizeInBits()-1);
- Value *In = Builder->CreateAShr(Op0, Sh, Op0->getName()+".lobit");
+ Op0->getType()->getScalarSizeInBits() - 1);
+ Value *In = Builder->CreateAShr(Op0, Sh, Op0->getName() + ".lobit");
if (In->getType() != CI.getType())
In = Builder->CreateIntCast(In, CI.getType(), true/*SExt*/);
- if (Pred == ICmpInst::ICMP_SGT)
- In = Builder->CreateNot(In, In->getName()+".not");
+ // Invert the sign bit if the comparison was checking for 'is positive'.
+ if (Pred == ICmpInst::ICMP_SGT || Pred == ICmpInst::ICMP_SGE)
+ In = Builder->CreateNot(In, In->getName() + ".not");
+
return replaceInstUsesWith(CI, In);
}
}
diff --git a/llvm/test/Transforms/InstCombine/vec_sext.ll b/llvm/test/Transforms/InstCombine/vec_sext.ll
index 6f0d21476e3..670789af050 100644
--- a/llvm/test/Transforms/InstCombine/vec_sext.ll
+++ b/llvm/test/Transforms/InstCombine/vec_sext.ll
@@ -43,3 +43,31 @@ entry:
; CHECK: and <4 x i32> %b.lobit.not, %sub
; CHECK: or <4 x i32> %0, %1
}
+
+;;; PR26701: https://llvm.org/bugs/show_bug.cgi?id=26701
+
+; Signed-less-than-or-equal to -1 is the same operation as above: smear the sign bit.
+
+define <2 x i32> @is_negative(<2 x i32> %a) {
+ %cmp = icmp sle <2 x i32> %a, <i32 -1, i32 -1>
+ %sext = sext <2 x i1> %cmp to <2 x i32>
+ ret <2 x i32> %sext
+
+; CHECK-LABEL: @is_negative(
+; CHECK-NEXT: ashr <2 x i32> %a, <i32 31, i32 31>
+; CHECK-NEXT: ret <2 x i32>
+}
+
+; Signed-greater-than-or-equal to 0 is 'not' of the same operation as above.
+
+define <2 x i32> @is_positive(<2 x i32> %a) {
+ %cmp = icmp sge <2 x i32> %a, zeroinitializer
+ %sext = sext <2 x i1> %cmp to <2 x i32>
+ ret <2 x i32> %sext
+
+; CHECK-LABEL: @is_positive(
+; CHECK-NEXT: [[SHIFT:%[a-zA-Z0-9.]+]] = ashr <2 x i32> %a, <i32 31, i32 31>
+; CHECK-NEXT: xor <2 x i32> [[SHIFT]], <i32 -1, i32 -1>
+; CHECK-NEXT: ret <2 x i32>
+}
+
OpenPOWER on IntegriCloud