experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Populating memory bandwidth information in the DeviceDescription, using information from the call to hipGetDeviceProperties

Browse Source
This commit is contained in:
Deven Desai 2020-04-08 22:44:41 +00:00
parent 8f4f90992c
commit aa39573ee1
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
tensorflow/stream_executor/rocm/rocm_gpu_executor.cc
View File

@ -856,6 +856,11 @@ GpuExecutor::CreateDeviceDescription(int device_ordinal) {
float clock_rate_ghz = static_cast<float>(prop.clockRate) / 1e6; float clock_rate_ghz = static_cast<float>(prop.clockRate) / 1e6;
builder.set_clock_rate_ghz(clock_rate_ghz); builder.set_clock_rate_ghz(clock_rate_ghz);
// mem_bandwidth = 2 * mem_bus_width_in_bytes * mem_clock_rate_in_hz
int64 memory_bandwidth = 2 * (int64(prop.memoryBusWidth) / 8) *
(int64(prop.memoryClockRate) * 1000);
builder.set_memory_bandwidth(memory_bandwidth);
} }
{ {