AI/rocm-systems
2
0
Tükrözés 0
Kód Hibajegyek Egyesítési kérések Actions Packages Projektek Kiadások Wiki Tevékenység

P4 to Git Change 1775995 by gandryey@gera-w8 on 2019/04/29 13:46:53

Forráskód böngészése 
SWDEV-79445 - OCL generic changes and code clean-up
	- Enable P2P extension for PAL path, currently it's staging copy only
	- Fix P2P staging copy

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#55 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#243 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#336 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#130 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#77 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#131 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#59 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#124 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#36 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#74 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#92 edit
This commit is contained in:
foreman
2019-04-29 13:58:26 -04:00
szülő 1dddb78021
commit 1e33e8be4d
10 fájl változott, egészen pontosan 210 új sor hozzáadva és 45 régi sor törölve
Download Patch File Download Diff File Expand all files Collapse all files
rocclr/runtime/device/rocm/rocvirtual.cpp
+10 -7
Fájl megtekintése
@@ -1253,6 +1253,12 @@ void VirtualGPU::submitCopyMemoryP2P(amd::CopyMemoryP2PCommand& cmd) {
size, cmd.isEntireMemory());
}
else {
amd::ScopedLock lock(dev().P2PStageOps());
Memory* dstStgMem = static_cast<Memory*>(
dev().P2PStage()->getDeviceMemory(*cmd.source().getContext().devices()[0]));
Memory* srcStgMem = static_cast<Memory*>(
dev().P2PStage()->getDeviceMemory(*cmd.destination().getContext().devices()[0]));
size_t copy_size = Device::kP2PStagingSize;
size_t left_size = size[0];
result = true;
@@ -1265,14 +1271,11 @@ void VirtualGPU::submitCopyMemoryP2P(amd::CopyMemoryP2PCommand& cmd) {
amd::Coord3D cpSize(copy_size);
// Perform 2 step transfer with staging buffer
// todo: optimization can be done with double buffering if events tracking
// will be propagated outside of the device transfers object
result &= dev().xferMgr().copyBuffer(*srcDevMem, *(dev().P2PStages()[0]), srcOrigin,
stageOffset, cpSize, cmd.isEntireMemory());
result &= dev().xferMgr().copyBuffer(
*srcDevMem, *dstStgMem, srcOrigin, stageOffset, cpSize);
srcOrigin.c[0] += copy_size;
result &= dstDevMem->dev().xferMgr().copyBuffer(*dstDevMem->dev().P2PStages()[0],
*dstDevMem, stageOffset, dstOrigin,
copy_size, cmd.isEntireMemory());
result &= dstDevMem->dev().xferMgr().copyBuffer(
*srcStgMem, *dstDevMem, stageOffset, dstOrigin, cpSize);
dstOrigin.c[0] += copy_size;
} while (left_size > 0);
}