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

SWDEV-301667 - Use large signal pool

Browse Source 
Use large signal pool if profiler is connected or profiling forced
enabled. This is needed to mitigate signal creation overhead when
profiling as signals are attached to every packet and deeper batch may
show overhead of signal allocation.

Change-Id: I8034b8a20b55328b87d593bf044f59672f9653e8
This commit is contained in:
Saleel Kudchadker
2023-08-24 17:36:00 +00:00
parent 077311153a
commit 1ec0ba3537
2 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rocclr/device/rocm/rocvirtual.cpp
+3
View File
@@ -341,6 +341,9 @@ VirtualGPU::HwQueueTracker::~HwQueueTracker() {
// ================================================================================================
bool VirtualGPU::HwQueueTracker::Create() {
uint kSignalListSize = ROC_SIGNAL_POOL_SIZE;
if (activity_prof::IsEnabled(OP_ID_DISPATCH) || gpu_.profiling_) {
kSignalListSize = !flagIsDefault(ROC_SIGNAL_POOL_SIZE) ? ROC_SIGNAL_POOL_SIZE : 4 * Ki;
}
signal_list_.resize(kSignalListSize);
hsa_agent_t agent = gpu_.gpu_device();