[Beignet] [PATCH] GBE: Fix type size for vector3
Ruiling Song
ruiling.song at intel.com
Thu Aug 7 20:21:09 PDT 2014
According to OCL spec, size of vector3 are aligned to vector4.
And for memory load/store, clang already aligned it to vector4.
If we do not calculate private/local memory size as vector4,
out of range memory access will appear.
This can fix the failure of opencv 3.0 case:
OCL_Arithm/MeanStdDev.Mat_Mask
Signed-off-by: Ruiling Song <ruiling.song at intel.com>
---
backend/src/llvm/llvm_passes.cpp | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/backend/src/llvm/llvm_passes.cpp b/backend/src/llvm/llvm_passes.cpp
index b8ab844..1a38a0c 100644
--- a/backend/src/llvm/llvm_passes.cpp
+++ b/backend/src/llvm/llvm_passes.cpp
@@ -181,7 +181,9 @@ namespace gbe
case Type::VectorTyID:
{
const VectorType* VecTy = cast<VectorType>(Ty);
- return VecTy->getNumElements() * getTypeBitSize(unit, VecTy->getElementType());
+ uint32_t numElem = VecTy->getNumElements();
+ if(numElem == 3) numElem = 4; // OCL spec
+ return numElem * getTypeBitSize(unit, VecTy->getElementType());
}
case Type::ArrayTyID:
{
--
1.7.10.4
More information about the Beignet
mailing list