summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
diff options
context:
space:
mode:
authorDorit Nuzman <dorit.nuzman@intel.com>2018-10-14 07:06:16 +0000
committerDorit Nuzman <dorit.nuzman@intel.com>2018-10-14 07:06:16 +0000
commit8174368955177c0765977996b00a0184921d5420 (patch)
tree68ae87abe77ac7844dd6dae68522339840ebf075 /llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
parent20fa085d74336f1f5801aa53d47039adbf116a82 (diff)
downloadbcm5719-llvm-8174368955177c0765977996b00a0184921d5420.tar.gz
bcm5719-llvm-8174368955177c0765977996b00a0184921d5420.zip
[IAI,LV] Add support for vectorizing predicated strided accesses using masked
interleave-group The vectorizer currently does not attempt to create interleave-groups that contain predicated loads/stores; predicated strided accesses can currently be vectorized only using masked gather/scatter or scalarization. This patch makes predicated loads/stores candidates for forming interleave-groups during the Loop-Vectorizer's analysis, and adds the proper support for masked-interleave- groups to the Loop-Vectorizer's planning and transformation stages. The patch also extends the TTI API to allow querying the cost of masked interleave groups (which each target can control); Targets that support masked vector loads/ stores may choose to enable this feature and allow vectorizing predicated strided loads/stores using masked wide loads/stores and shuffles. Reviewers: Ayal, hsaito, dcaballe, fhahn, javed.absar Reviewed By: Ayal Differential Revision: https://reviews.llvm.org/D53011 llvm-svn: 344472
Diffstat (limited to 'llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp')
-rw-r--r--llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp6
1 files changed, 5 insertions, 1 deletions
diff --git a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
index 6f553d5bed3..1eaeb9699bf 100644
--- a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
+++ b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
@@ -909,7 +909,11 @@ int SystemZTTIImpl::getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy,
unsigned Factor,
ArrayRef<unsigned> Indices,
unsigned Alignment,
- unsigned AddressSpace) {
+ unsigned AddressSpace,
+ bool IsMasked) {
+ if (IsMasked)
+ return BaseT::getInterleavedMemoryOpCost(Opcode, VecTy, Factor, Indices,
+ Alignment, AddressSpace, IsMasked);
assert(isa<VectorType>(VecTy) &&
"Expect a vector type for interleaved memory op");
OpenPOWER on IntegriCloud