Align DeepSeek and GLM execution with DS4

native/metal/ds4_canary.m

@@ -0,0 +1,66 @@
+#import <Foundation/Foundation.h>
+#import <Metal/Metal.h>
+#include <mach/mach_time.h>
+#include <time.h>
+#include "ds4_gpu.h"
+
+/* Shared optional UI/headless probe. Process placement matters: a separate
+ * queue in the model process is not a separate-process scheduling test. */
+static id<MTLDevice> g_canary_device;
+static id<MTLCommandQueue> g_canary_queue;
+static id<MTLBuffer> g_canary_buffer;
+
+static double ds4_monotonic_seconds(void) {
+    struct timespec time;
+    if (clock_gettime(CLOCK_MONOTONIC, &time) != 0) return 0.0;
+    return (double)time.tv_sec + (double)time.tv_nsec / 1000000000.0;
+}
+
+int ds4_gpu_canary_probe(ds4_gpu_canary_sample *sample) {
+    if (!sample) return 0;
+    sample->scheduled_seconds = 0.0;
+    sample->completed_seconds = 0.0;
+    sample->gpu_wait_seconds = -1.0;
+    sample->gpu_interval_seconds = -1.0;
+    sample->host_return_seconds = -1.0;
+    @autoreleasepool {
+        if (!g_canary_device) g_canary_device = MTLCreateSystemDefaultDevice();
+        if (!g_canary_queue && g_canary_device) {
+            g_canary_queue = [g_canary_device newCommandQueue];
+        }
+        if (!g_canary_buffer && g_canary_device) {
+            g_canary_buffer = [g_canary_device newBufferWithLength:4096
+                                                           options:MTLResourceStorageModeShared];
+        }
+        if (!g_canary_queue || !g_canary_buffer) return 0;
+
+        id<MTLCommandBuffer> cb = [g_canary_queue commandBuffer];
+        id<MTLBlitCommandEncoder> blit = [cb blitCommandEncoder];
+        if (!cb || !blit) return 0;
+        [blit fillBuffer:g_canary_buffer range:NSMakeRange(0, 4096) value:0];
+        [blit endEncoding];
+        mach_timebase_info_data_t timebase;
+        if (mach_timebase_info(&timebase) != KERN_SUCCESS || !timebase.denom) return 0;
+        const double scale = (double)timebase.numer / timebase.denom / 1e9;
+        const double started = ds4_monotonic_seconds();
+        const double mach_started = (double)mach_absolute_time() * scale;
+        [cb commit];
+        [cb waitUntilScheduled];
+        sample->scheduled_seconds = ds4_monotonic_seconds() - started;
+        [cb waitUntilCompleted];
+        const double mach_returned = (double)mach_absolute_time() * scale;
+        sample->completed_seconds = ds4_monotonic_seconds() - started;
+        // Metal GPU times use system mach time, unlike CLOCK_MONOTONIC on
+        // macOS. Read only after completion; unavailable timestamps stay -1.
+        const double gpu_start = cb.GPUStartTime;
+        const double gpu_end = cb.GPUEndTime;
+        if (gpu_start > 0.0 && gpu_start >= mach_started &&
+            gpu_end >= gpu_start && mach_returned >= gpu_end) {
+            sample->gpu_wait_seconds = gpu_start - mach_started;
+            // Includes GPU scheduling/preemption, not exclusive busy time.
+            sample->gpu_interval_seconds = gpu_end - gpu_start;
+            sample->host_return_seconds = mach_returned - gpu_end;
+        }
+        return cb.status == MTLCommandBufferStatusCompleted;
+    }
+}

native/metal/ds4_gpu.h

@@ -116,6 +116,9 @@ void ds4_gpu_busy_stats_get(ds4_gpu_busy_stats *stats);
 typedef struct {
     double scheduled_seconds;
     double completed_seconds;
+    double gpu_wait_seconds;
+    double gpu_interval_seconds;
+    double host_return_seconds;
 } ds4_gpu_canary_sample;
 int ds4_gpu_canary_probe(ds4_gpu_canary_sample *sample);
 #ifdef __APPLE__

native/metal/ds4_metal.m

@@ -1201,48 +1201,6 @@ static void ds4_gpu_busy_stats_record(id<MTLCommandBuffer> cb, uint64_t epoch) {
     }
 }
 
-/* A separate queue used by the headless evaluator's supervisor process.  The
- * tiny blit measures whether another process can still schedule UI-sized GPU
- * work while the model owns its own Metal queue. */
-static id<MTLDevice> g_canary_device;
-static id<MTLCommandQueue> g_canary_queue;
-static id<MTLBuffer> g_canary_buffer;
-
-static double ds4_monotonic_seconds(void) {
-    struct timespec time;
-    if (clock_gettime(CLOCK_MONOTONIC, &time) != 0) return 0.0;
-    return (double)time.tv_sec + (double)time.tv_nsec / 1000000000.0;
-}
-
-int ds4_gpu_canary_probe(ds4_gpu_canary_sample *sample) {
-    if (!sample) return 0;
-    sample->scheduled_seconds = 0.0;
-    sample->completed_seconds = 0.0;
-    @autoreleasepool {
-        if (!g_canary_device) g_canary_device = MTLCreateSystemDefaultDevice();
-        if (!g_canary_queue && g_canary_device) {
-            g_canary_queue = [g_canary_device newCommandQueue];
-        }
-        if (!g_canary_buffer && g_canary_device) {
-            g_canary_buffer = [g_canary_device newBufferWithLength:4096
-                                                           options:MTLResourceStorageModeShared];
-        }
-        if (!g_canary_queue || !g_canary_buffer) return 0;
-
-        id<MTLCommandBuffer> cb = [g_canary_queue commandBuffer];
-        id<MTLBlitCommandEncoder> blit = [cb blitCommandEncoder];
-        if (!cb || !blit) return 0;
-        [blit fillBuffer:g_canary_buffer range:NSMakeRange(0, 4096) value:0];
-        [blit endEncoding];
-        const double started = ds4_monotonic_seconds();
-        ds4_gpu_commit_command_buffer(cb);
-        [cb waitUntilScheduled];
-        sample->scheduled_seconds = ds4_monotonic_seconds() - started;
-        [cb waitUntilCompleted];
-        sample->completed_seconds = ds4_monotonic_seconds() - started;
-        return cb.status == MTLCommandBufferStatusCompleted;
-    }
-}
 
 /* A failed command buffer can leave a cross-threadgroup arrival counter at an
  * arbitrary partial value.  Drop cached ownership instead of CPU-resetting