From 25b674eabdb92212a6d8149d6616b2af59317695 Mon Sep 17 00:00:00 2001
From: Takoroka <137927095+Takoroka@users.noreply.github.com>
Date: Wed, 28 Oct 2026 23:07:49 -0400
Subject: 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.
---
 src/common/cpu_features.cpp | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'src/common')

diff --git a/src/common/cpu_features.cpp b/src/common/cpu_features.cpp
index 8ccb6847f7..52fd003c44 100644
--- a/src/common/cpu_features.cpp
+++ b/src/common/cpu_features.cpp
@@ -225,6 +225,13 @@ const CPUCaps g_cpu_caps = [] {
         }
     }
 
+    // AMD CPUs have no leaf 0x15 (Zen 4 stops at 0x10): measure their invariant TSC too, or every
+    // guest clock read (CNTPCT, which games read thousands of times a frame) goes through the
+    // host's much slower QueryPerformanceCounter.
+    if (caps.invariant_tsc && caps.tsc_frequency == 0) {
+        caps.tsc_frequency = X64::EstimateRDTSCFrequency();
+    }
+
     if (max_std_fn >= 0x16) {
         __cpuid(cpu_id, 0x16);
         caps.base_frequency = cpu_id[0];
-- 
cgit v1.2.3