P4 to Git Change 1451293 by gandryey@gera-w8 on 2017/08/24 13:37:00

SWDEV-129129 - [[CQE OCL][Vega vs Fiji] Upto 12% Performance drop observed on VEGA10 compared to FIJI while running BlackMagic Davinci Resolve
	The app creates/destroys hundred resources each frame. PAL path was removing the destroyed resources from the resident list, although the resource was kept in the cache. This change does the follwoing:
	- Switch TS tracking from a map in VirtualGPU to resource
	- Don't remove references until the actual memory destruction
	- Add a residency threshold to avoid OS resident/eviction calls

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/blit.hpp#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.cpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.hpp#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldefs.hpp#19 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#50 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.hpp#17 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#35 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.hpp#13 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palmemory.cpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#46 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.hpp#19 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#30 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.hpp#13 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#52 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#28 edit


[ROCm/clr commit: b82be1113f]

projects/clr/rocclr/runtime/device/pal/paldevice.cpp

@@ -581,7 +581,10 @@ Device::Device()
       heapInitComplete_(false),
       xferQueue_(nullptr),
       globalScratchBuf_(nullptr),
-      srdManager_(nullptr) {}
+      srdManager_(nullptr),
+      lockResourceOps_(nullptr),
+      resourceList_(nullptr)
+      {}
 
 Device::~Device() {
   // remove the HW debug manager
@@ -625,6 +628,8 @@ Device::~Device() {
   delete vgpusAccess_;
   delete scratchAlloc_;
   delete mapCacheOps_;
+  delete lockResourceOps_;
+  delete resourceList_;
 
   if (context_ != nullptr) {
     context_->release();
@@ -639,7 +644,10 @@ bool Device::create(Pal::IDevice* device) {
   if (!amd::Device::create()) {
     return false;
   }
-
+  resourceList_ = new std::list<GpuMemoryReference*>();
+  if (nullptr == resourceList_) {
+    return false;
+  }
   appProfile_.init();
   device_ = device;
   Pal::Result result;
@@ -749,6 +757,11 @@ bool Device::create(Pal::IDevice* device) {
     return false;
   }
 
+  lockResourceOps_ = new amd::Monitor("Resource List Ops Lock", true);
+  if (nullptr == lockResourceOps_) {
+    return false;
+  }
+
   lockForInitHeap_ = new amd::Monitor("Async Ops Lock For Initialization of Heap Resource", true);
   if (nullptr == lockForInitHeap_) {
     return false;
@@ -2075,9 +2088,9 @@ bool Device::createBlitProgram() {
   return result;
 }
 
-void Device::SrdManager::fillResourceList(std::vector<const Memory*>& memList) {
+void Device::SrdManager::fillResourceList(VirtualGPU& gpu) {
   for (uint i = 0; i < pool_.size(); ++i) {
-    memList.push_back(pool_[i].buf_);
+    gpu.addVmMemory(pool_[i].buf_);
   }
 }