nx2: profile engine method calls and semaphore acquires; notes 140-141

EDEN_NX2_GPU_PROFILE now times engine method calls (the work a split GPU thread's back half
would run) and counts semaphore acquires and those that wait. Title 1: method calls ~343 ms
a second (6.9 million), front-half work (command parsing, macros) ~333 ms, acquires ~2,700 a
second of which ~220 wait. Notes 140 (macro compiler) and 141 (draw setup).

1 files changed, 3 insertions, 0 deletions

diff --git a/src/video_core/dma_pusher.cpp b/src/video_core/dma_pusher.cpp
index 3cc5afe967..44a63d789a 100644
--- a/src/video_core/dma_pusher.cpp
+++ b/src/video_core/dma_pusher.cpp
@@ -12,6 +12,7 @@
 #include "common/settings.h"
 #include "core/core.h"
 #include "core/memory.h"
+#include "video_core/nx2_profile.h"
 #include "video_core/dma_pusher.h"
 #include "video_core/control/channel_state.h"
 #include "video_core/engines/maxwell_3d.h"
@@ -335,6 +336,7 @@ void DmaPusher::CallMethod(u32 argument) {
         if (!subchannel->execution_mask[dma_state.method]) {
             subchannel->method_sink.emplace_back(dma_state.method, argument);
         } else {
+            VideoCommon::Nx2Profile::Scope method_scope{VideoCommon::Nx2Profile::Zone::Method};
             subchannel->ConsumeSink(system);
             subchannel->current_dma_segment = dma_state.dma_get + dma_state.dma_word_offset;
             subchannel->CallMethod(system, dma_state.method, argument, dma_state.is_last_call);
@@ -356,6 +358,7 @@ void DmaPusher::CallMultiMethod(const u32* base_start, u32 num_methods) {
             ReportUnboundSubchannel();
             return;
         }
+        VideoCommon::Nx2Profile::Scope method_scope{VideoCommon::Nx2Profile::Zone::Method};
         subchannel->ConsumeSink(system);
         subchannel->current_dma_segment = dma_state.dma_get + dma_state.dma_word_offset;
         subchannel->CallMultiMethod(system, dma_state.method, base_start, num_methods, dma_state.method_count);