nx2: measure the TSC on AMD, no rethrows for rejected shaders, debug hooks off the hot path

- AMD CPUs have no CPUID leaf 0x15, so the TSC frequency stayed 0 and
  every guest CNTPCT read went through QueryPerformanceCounter (~10% of
  the game's main core in title 1). Measure it like Intel CPUs without
  a crystal frequency.
- A rejected native shader was rethrown (two C++ throws) every time it
  was bound; return false instead (~1-2% of the GPU thread).
- The semaphore watch, pushbuffer entry hashing, first-write trace and
  per-macro debug logs ran on every command word or macro call; they
  now cost a flag check unless their environment variable is set
  (~4% of the GPU thread). Also starts the macro engine's profile zone.

1 files changed, 12 insertions, 0 deletions

diff --git a/src/video_core/shader_cache.cpp b/src/video_core/shader_cache.cpp
index da5417be02..73a2bf6646 100644
--- a/src/video_core/shader_cache.cpp
+++ b/src/video_core/shader_cache.cpp
@@ -79,6 +79,13 @@ bool ShaderCache::RefreshStages(std::array<u64, 6>& unique_hashes) try {
             return false;
         }
         const ShaderInfo* shader_info{TryGet(*cpu_shader_addr)};
+        if (!shader_info && native && IsRejected(*cpu_shader_addr)) {
+            // A rejected program fails the same way every time it is bound: skip its draws
+            // without rethrowing (two C++ throws each time cost ~1-2% of the GPU thread).
+            maxwell3d->GetNativeMacroEngine().native_execution_failed = true;
+            last_shaders_valid = false;
+            return false;
+        }
         if (!shader_info) {
             const u32 start_address{native ? 0 : shader_config.offset};
             try {
@@ -165,6 +172,11 @@ void ShaderCache::RethrowIfRejected(VAddr addr) {
     }
 }
 
+bool ShaderCache::IsRejected(VAddr addr) {
+    std::scoped_lock lock{rejected_mutex};
+    return rejected_native.contains(addr);
+}
+
 void ShaderCache::RememberRejection(VAddr addr) {
     std::scoped_lock lock{rejected_mutex};
     rejected_native.emplace(addr, std::current_exception());