From 85374b6b31dc3ea3edadc5caf2bc7bc40f704643 Mon Sep 17 00:00:00 2001
From: foreman <dl.constructicon@amd.com>
Date: Wed, 18 Jan 2017 09:59:38 -0500
Subject: [PATCH] P4 to Git Change 1363243 by jatang@jatang-opencl-hsa-stg1 on
 2017/01/18 09:49:05

	SWDEV-95919 - Fix num-of-waves PerfCounter is 0 on Baffin.

	Counters are clockgated on Fiji and above. Need to program the RLC_PERFMON_CLK_CNTL register thru IDeviceSetClockMode(), so that meaningful data is recorded. We leave kmd/pplib to keep track of the OCL process to restore the RLC_PERFMON_CLK_CNTL register when the OCL process is killed.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#41 edit


[ROCm/clr commit: e826e296d40a850a220382159d54bcda961000b1]
---
 projects/clr/rocclr/runtime/device/pal/palvirtual.cpp | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/projects/clr/rocclr/runtime/device/pal/palvirtual.cpp b/projects/clr/rocclr/runtime/device/pal/palvirtual.cpp
index 6ee31cfbc5..54bee9dbfa 100644
--- a/projects/clr/rocclr/runtime/device/pal/palvirtual.cpp
+++ b/projects/clr/rocclr/runtime/device/pal/palvirtual.cpp
@@ -2507,7 +2507,15 @@ VirtualGPU::submitPerfCounter(amd::PerfCounterCommand& vcmd)
             palPerf = counter->iPerf();
             // Find the state and sends the command to PAL
             if (vcmd.getState() == amd::PerfCounterCommand::Begin) {
+                Pal::SetClockModeInput  input;
+                Pal::SetClockModeOutput output = {};
+                input.clockMode = Pal::DeviceClockMode::Profiling;
+                dev().iDev()->SetClockMode(input, &output);
+                GpuEvent event;
+                eventBegin(MainEngine);
                 iCmd()->CmdBeginPerfExperiment(palPerf);
+                eventEnd(MainEngine, event);
+                setGpuEvent(event);
             }
             else if (vcmd.getState() == amd::PerfCounterCommand::End) {
                 GpuEvent event;