feat(gpu-log): add gpu_log_ids.h — single source of truth for ring IDs

crates/ml-alpha/cuda/gpu_log_ids.h

@@ -0,0 +1,39 @@
+// gpu_log_ids.h — single source of truth for log-ring kernel/record IDs.
+//
+// Both kernel-side (#include from .cu files) and Rust-side decoder reference
+// these symbols. Drift between them is checked by `build.rs` (Task 2).
+//
+// kernel_id (uint8) — which kernel emitted the record.
+// record_type (uint8) — sub-type within the kernel (input/state/output/debug).
+// payload layout — defined per (kernel_id, record_type) in decoder.
+
+#ifndef GPU_LOG_IDS_H
+#define GPU_LOG_IDS_H
+
+#define GPU_LOG_N_KERNELS         8
+#define GPU_LOG_N_RT_PER_KERNEL   4
+#define GPU_LOG_N_RECORDS_PER_STEP (GPU_LOG_N_KERNELS * GPU_LOG_N_RT_PER_KERNEL)
+#define GPU_LOG_N_SLOTS           32768
+#define GPU_LOG_RECORD_BYTES      64
+#define GPU_LOG_PAYLOAD_F32       12
+#define GPU_LOG_MAGIC             0xF0F0A710u
+
+// Kernel IDs (uint8). Add new kernels at the bottom; never reorder.
+#define KID_SMOOTHNESS_CONTROLLER  0
+#define KID_OUTPUT_SMOOTHNESS      1
+#define KID_BCE_MULTI_HORIZON      2
+#define KID_HORIZON_LAMBDA         3
+#define KID_HEADS_GRN_FWD          4
+#define KID_HEADS_GRN_BWD          5
+#define KID_CFC_STEP               6
+#define KID_RESERVED_7             7
+
+// Record types within a kernel (uint8). Reuse RT_INPUT/STATE/OUTPUT/DEBUG
+// across kernels — payload layout differs per (kid, rt) pair but the four
+// roles are conventional.
+#define RT_INPUT   0
+#define RT_STATE   1
+#define RT_OUTPUT  2
+#define RT_DEBUG   3
+
+#endif // GPU_LOG_IDS_H