P4 to Git Change 2008906 by axie@axie-hip-vdi-pal2 on 2019/10/04 18:55:34

SWDEV-189650 - [HIP-CLANG][HIP/VDI/PAL] Hangs on test hip_threadfence_system
	1. In HIP + VDI + ROCm, allow SVM atomic in VEGA10 and later ASIC. GFX8 (Tonga) was enabled before.
	2. In HIP + VDI + PAL Linux driver, allow SVM atomic in VEGA10 and later ASIC.

	Tests:
	1. In HIP + VDI + ROCm, hip_threadfence_system test passed.
	2. In HIP + VDI + PAL + Linux , hip_threadfence_system test passed.
	3. OpenCL + PAL, clinfo and ocltest runtime test pass.
	4. OpenCL + ROCM, clinfo and ocltest runtime test pass.
	5. Windows 10, VEGA 10, clinfo and and ocltest runtime test pass. hip_threadfence_system test passed by skipping the test.

	Teamcity presubmission test:
	http://ocltc.amd.com:8111/viewModification.html?modId=127083&personal=true&tab=vcsModificationBuilds
	http://ocltc.amd.com:8111/viewModification.html?modId=127076&personal=true&tab=vcsModificationBuilds

	ReviewBoard: http://ocltc.amd.com/reviews/r/18077/

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#73 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#171 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#80 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.hpp#31 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#134 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocmemory.cpp#44 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#320 edit

rocclr/runtime/device/rocm/rocdevice.cpp

@@ -1325,7 +1325,13 @@ bool Device::populateOCLDeviceConstants() {
     if (agent_profile_ == HSA_PROFILE_FULL) {
       info_.svmCapabilities_ |= CL_DEVICE_SVM_FINE_GRAIN_SYSTEM;
     }
-    if (!settings().useLightning_) {
+    if (amd::IS_HIP) {
+      // Report atomics capability based on GFX IP, control on Hawaii
+      if (info_.hostUnifiedMemory_ || deviceInfo_.gfxipVersion_ >= 800) {
+        info_.svmCapabilities_ |= CL_DEVICE_SVM_ATOMICS;
+      }
+    }
+    else if (!settings().useLightning_) {
       // Report atomics capability based on GFX IP, control on Hawaii
       // and Vega10.
       if (info_.hostUnifiedMemory_ ||

rocclr/runtime/device/rocm/rocmemory.cpp

@@ -697,7 +697,12 @@ bool Buffer::create() {
 
     if (owner()->getSvmPtr() == reinterpret_cast<void*>(1)) {
       if (isFineGrain) {
-        deviceMemory_ = dev().hostAlloc(size(), 1, false);
+        if (memFlags & CL_MEM_SVM_ATOMICS) {
+          deviceMemory_ = dev().hostAlloc(size(), 1, true);
+        }
+        else {
+          deviceMemory_ = dev().hostAlloc(size(), 1, false);
+        }
         flags_ |= HostMemoryDirectAccess;
       } else {
         deviceMemory_ = dev().deviceLocalAlloc(size());