maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

There is a trunc(lshr (zext A), Cst) optimization in InstCombineCasts that 

removes cast by performing the lshr on smaller types. However, currently there
is no trunc(lshr (sext A), Cst) variant.
This patch add such optimization by transforming trunc(lshr (sext A), Cst)
to ashr A, Cst.

Differential Revision: http://reviews.llvm.org/D12520

llvm-svn: 246997
This commit is contained in:
Jakub Kuderski 2015-09-08 10:03:17 +00:00
parent d96d89f6e5
commit 7cd4810021
2 changed files with 57 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
View File

@ -499,6 +499,26 @@ Instruction *InstCombiner::visitTrunc(TruncInst &CI) {
return CastInst::CreateIntegerCast(Shift, CI.getType(), false);
}
// Transform trunc(lshr (sext A), Cst) to ashr A, Cst to eliminate type
// conversion.
// It works because bits coming from sign extension have the same value as
// sign bit of the original value; performing ashr instead of lshr
// generates bits of the same value as the sign bit.
if (Src->hasOneUse() &&
match(Src, m_LShr(m_SExt(m_Value(A)), m_ConstantInt(Cst))) &&
cast<Instruction>(Src)->getOperand(0)->hasOneUse()) {
const unsigned ASize = A->getType()->getPrimitiveSizeInBits();
// This optimization can be only performed when zero bits generated by
// the original lshr aren't pulled into the value after truncation, so we
// can only shift by values smaller then the size of destination type (in
// bits).
if (Cst->getValue().ult(ASize)) {
Value *Shift = Builder->CreateAShr(A, Cst->getZExtValue());
Shift->takeName(Src);
return CastInst::CreateIntegerCast(Shift, CI.getType(), false);
}
}
// Transform "trunc (and X, cst)" -> "and (trunc X), cst" so long as the dest
// type isn't non-native.
if (Src->hasOneUse() && isa<IntegerType>(Src->getType()) &&

37
llvm/test/Transforms/InstCombine/cast.ll
View File

@ -1062,6 +1062,43 @@ define i8 @test85(i32 %a) {
; CHECK: [[CST:%.*]] = trunc i32 [[SHR]] to i8
}
define i16 @test86(i16 %v) {
%a = sext i16 %v to i32
%s = ashr i32 %a, 4
%t = trunc i32 %s to i16
ret i16 %t
; CHECK-LABEL: @test86(
; CHECK: [[ASHR:%.*]] = ashr i16 %v, 4
; CHECK-NEXT: ret i16 [[ASHR]]
}
define i16 @test87(i16 %v) {
%c = sext i16 %v to i32
%m = mul nsw i32 %c, 16
%a = ashr i32 %m, 16
%t = trunc i32 %a to i16
ret i16 %t
; CHECK-LABEL: @test87(
; CHECK: [[ASHR:%.*]] = ashr i16 %v, 12
; CHECK-NEXT: ret i16 [[ASHR]]
}
define i16 @test88(i16 %v) {
%a = sext i16 %v to i32
%s = ashr i32 %a, 18
%t = trunc i32 %s to i16
ret i16 %t
; Do not optimize to ashr i16 (shift by 18)
; CHECK-LABEL: @test88(
; CHECK: [[SEXT:%.*]] = sext i16 %v to i32
; CHECK-NEXT: [[ASHR:%.*]] = ashr i32 [[SEXT]], 18
; CHECK-NEXT: [[TRUNC:%.*]] = trunc i32 [[ASHR]] to i16
; CHECK-NEXT: ret i16 [[TRUNC]]
}
; Overflow on a float to int or int to float conversion is undefined (PR21130).
define i8 @overflow_fptosi() {