AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

P4 to Git Change 1568521 by gandryey@gera-w8 on 2018/06/14 17:43:52

Browse Source 
SWDEV-79445 - OCL generic changes and code clean-up
	- Change LDS setup to account the size, since LC forces 4 bytes for LDS offsets always

	http://ocltc.amd.com/reviews/r/15197/

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_execute.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_program.cpp#49 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpublit.cpp#130 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#327 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.cpp#25 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#56 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#109 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.hpp#11 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#38 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#88 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.cpp#34 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.hpp#25 edit
This commit is contained in:
foreman
2018-06-14 17:51:35 -04:00
parent c149902a4d
commit f6d8feabeb
10 changed files with 127 additions and 131 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rocclr/runtime/device/pal/palvirtual.cpp
+17 -7
View File
@@ -3041,14 +3041,24 @@ bool VirtualGPU::processMemObjectsHSA(const amd::Kernel& kernel, const_address p
// Find if current argument is a buffer
if (desc.type_ == T_POINTER) {
// If it is a local pointer
if (desc.size_ == 0) {
if (desc.addressQualifier_ == CL_KERNEL_ARG_ADDRESS_LOCAL) {
ldsAddress = amd::alignUp(ldsAddress, desc.info_.arrayIndex_);
// Save the original LDS size
size_t ldsSize = *reinterpret_cast<const size_t*>(params + desc.offset_);
// Patch the LDS address in the original arguments with an LDS address(offset)
WriteAqlArgAt(const_cast<address>(params), &ldsAddress, sizeof(void*), desc.offset_);
// Add the original size
ldsAddress += ldsSize;
if (desc.size_ == 8) {
// Save the original LDS size
uint64_t ldsSize = *reinterpret_cast<const uint64_t*>(params + desc.offset_);
// Patch the LDS address in the original arguments with an LDS address(offset)
WriteAqlArgAt(const_cast<address>(params), &ldsAddress, desc.size_, desc.offset_);
// Add the original size
ldsAddress += ldsSize;
} else {
// Save the original LDS size
uint32_t ldsSize = *reinterpret_cast<const uint32_t*>(params + desc.offset_);
// Patch the LDS address in the original arguments with an LDS address(offset)
uint32_t ldsAddr = ldsAddress;
WriteAqlArgAt(const_cast<address>(params), &ldsAddr, desc.size_, desc.offset_);
// Add the original size
ldsAddress += ldsSize;
}
} else {
Memory* gpuMem = nullptr;
amd::Memory* mem = nullptr;