forked from OSchip/llvm-project
Allow controlling vectorization of boolean values separately from other integer types.
These are used as the result of comparisons, and often handled differently from larger integer types. llvm-svn: 159111
This commit is contained in:
parent
0a045bbe4e
commit
3099ce9489
|
@ -28,6 +28,9 @@ struct VectorizeConfig {
|
|||
/// @brief The size of the native vector registers.
|
||||
unsigned VectorBits;
|
||||
|
||||
/// @brief Vectorize boolean values.
|
||||
bool VectorizeBools;
|
||||
|
||||
/// @brief Vectorize integer values.
|
||||
bool VectorizeInts;
|
||||
|
||||
|
|
|
@ -76,6 +76,10 @@ MaxCandPairsForCycleCheck("bb-vectorize-max-cycle-check-pairs", cl::init(200),
|
|||
cl::Hidden, cl::desc("The maximum number of candidate pairs with which to use"
|
||||
" a full cycle check"));
|
||||
|
||||
static cl::opt<bool>
|
||||
NoBools("bb-vectorize-no-bools", cl::init(false), cl::Hidden,
|
||||
cl::desc("Don't try to vectorize boolean (i1) values"));
|
||||
|
||||
static cl::opt<bool>
|
||||
NoInts("bb-vectorize-no-ints", cl::init(false), cl::Hidden,
|
||||
cl::desc("Don't try to vectorize integer values"));
|
||||
|
@ -614,10 +618,15 @@ namespace {
|
|||
!(VectorType::isValidElementType(T2) || T2->isVectorTy()))
|
||||
return false;
|
||||
|
||||
if (!Config.VectorizeInts
|
||||
&& (T1->isIntOrIntVectorTy() || T2->isIntOrIntVectorTy()))
|
||||
return false;
|
||||
|
||||
if (T1->getScalarSizeInBits() == 1 && T2->getScalarSizeInBits() == 1) {
|
||||
if (!Config.VectorizeBools)
|
||||
return false;
|
||||
} else {
|
||||
if (!Config.VectorizeInts
|
||||
&& (T1->isIntOrIntVectorTy() || T2->isIntOrIntVectorTy()))
|
||||
return false;
|
||||
}
|
||||
|
||||
if (!Config.VectorizeFloats
|
||||
&& (T1->isFPOrFPVectorTy() || T2->isFPOrFPVectorTy()))
|
||||
return false;
|
||||
|
@ -1990,6 +1999,7 @@ llvm::vectorizeBasicBlock(Pass *P, BasicBlock &BB, const VectorizeConfig &C) {
|
|||
//===----------------------------------------------------------------------===//
|
||||
VectorizeConfig::VectorizeConfig() {
|
||||
VectorBits = ::VectorBits;
|
||||
VectorizeBools = !::NoBools;
|
||||
VectorizeInts = !::NoInts;
|
||||
VectorizeFloats = !::NoFloats;
|
||||
VectorizePointers = !::NoPointers;
|
||||
|
|
|
@ -1,5 +1,6 @@
|
|||
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128"
|
||||
; RUN: opt < %s -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s
|
||||
; RUN: opt < %s -bb-vectorize -bb-vectorize-req-chain-depth=3 -bb-vectorize-no-bools -instcombine -gvn -S | FileCheck %s -check-prefix=CHECK-NB
|
||||
|
||||
; Basic depth-3 chain with select
|
||||
define double @test1(double %A1, double %A2, double %B1, double %B2, i1 %C1, i1 %C2) {
|
||||
|
@ -30,6 +31,7 @@ define double @test1(double %A1, double %A2, double %B1, double %B2, i1 %C1, i1
|
|||
; Basic depth-3 chain with select (and vect. compare)
|
||||
define double @test2(double %A1, double %A2, double %B1, double %B2) {
|
||||
; CHECK: @test2
|
||||
; CHECK-NB: @test2
|
||||
; CHECK: %X1.v.i1.1 = insertelement <2 x double> undef, double %B1, i32 0
|
||||
; CHECK: %X1.v.i0.1 = insertelement <2 x double> undef, double %A1, i32 0
|
||||
; CHECK: %X1.v.i1.2 = insertelement <2 x double> %X1.v.i1.1, double %B2, i32 1
|
||||
|
@ -43,6 +45,7 @@ define double @test2(double %A1, double %A2, double %B1, double %B2) {
|
|||
%C1 = fcmp ogt double %X1, %A1
|
||||
%C2 = fcmp ogt double %X2, %A2
|
||||
; CHECK: %C1 = fcmp ogt <2 x double> %X1, %X1.v.i0.2
|
||||
; CHECK-NB: fcmp ogt double
|
||||
%Z1 = select i1 %C1, double %Y1, double %B1
|
||||
%Z2 = select i1 %C2, double %Y2, double %B2
|
||||
; CHECK: %Z1 = select <2 x i1> %C1, <2 x double> %Y1, <2 x double> %X1.v.i1.2
|
||||
|
|
Loading…
Reference in New Issue