Cycles: Useful Metal backend debug & profiling functionality

This patch adds some useful debugging & profiling env vars to the Metal backend:

- `CYCLES_METAL_PROFILING`: output a per-kernel timing report at the end of the render
- `CYCLES_METAL_DEBUG`: enable per-dispatch tracing (very verbose)
- `CYCLES_DEBUG_METAL_CAPTURE_KERNEL`: enable programatic .gputrace capture for a specified kernel index

Here's an example of the timing report with `CYCLES_METAL_PROFILING` enabled:

```
---------------------------------------------------------------------------------------------------
Kernel name                                 Total threads   Dispatches     Avg. T/D    Time   Time%
---------------------------------------------------------------------------------------------------
integrator_init_from_camera                   657,407,232          161    4,083,274   0.24s   0.51%
integrator_intersect_closest                1,629,288,440          681    2,392,494  15.18s  32.12%
integrator_intersect_shadow                   751,652,291          470    1,599,260   5.80s  12.28%
integrator_shade_background                   304,612,074          263    1,158,220   1.16s   2.45%
integrator_shade_surface                    1,159,764,041          676    1,715,627  20.57s  43.52%
integrator_shade_shadow                       598,885,847          418    1,432,741   1.27s   2.69%
integrator_queued_paths_array               2,969,650,130          805    3,689,006   0.35s   0.74%
integrator_queued_shadow_paths_array          593,936,619          379    1,567,115   0.14s   0.29%
integrator_terminated_paths_array              22,205,417          155      143,260   0.05s   0.10%
integrator_sorted_paths_array               2,517,140,043          676    3,723,579   1.65s   3.50%
integrator_compact_paths_array                648,912,748          155    4,186,533   0.03s   0.07%
integrator_compact_states                      20,872,687          155      134,662   0.14s   0.29%
integrator_terminated_shadow_paths_array      374,100,675          438      854,111   0.16s   0.33%
integrator_compact_shadow_paths_array         503,768,657          438    1,150,156   0.05s   0.10%
integrator_compact_shadow_states               37,664,941          202      186,460   0.23s   0.50%
integrator_reset                               25,165,824            6    4,194,304   0.06s   0.12%
film_convert_combined_half_rgba                 3,110,400            6      518,400   0.00s   0.01%
prefix_sum                                            676          676            1   0.19s   0.40%
---------------------------------------------------------------------------------------------------
                                                                 6,760               47.27s 100.00%
---------------------------------------------------------------------------------------------------
```

Reviewed By: brecht

Differential Revision: https://developer.blender.org/D15044

1 files changed, 2 insertions, 2 deletions

diff --git a/intern/cycles/kernel/device/gpu/kernel.h b/intern/cycles/kernel/device/gpu/kernel.h
index 6405e365847..d657571a5fa 100644
--- a/intern/cycles/kernel/device/gpu/kernel.h
+++ b/intern/cycles/kernel/device/gpu/kernel.h
@@ -241,7 +241,7 @@ ccl_gpu_kernel(GPU_KERNEL_BLOCK_NUM_THREADS, GPU_KERNEL_MAX_REGISTERS)
 }
 ccl_gpu_kernel_postfix
 
-#ifdef __KERNEL_METAL__
+#if defined(__KERNEL_METAL_APPLE__) && defined(__METALRT__)
 constant int __dummy_constant [[function_constant(0)]];
 #endif
 
@@ -256,7 +256,7 @@ ccl_gpu_kernel(GPU_KERNEL_BLOCK_NUM_THREADS, GPU_KERNEL_MAX_REGISTERS)
   if (global_index < work_size) {
     const int state = (path_index_array) ? path_index_array[global_index] : global_index;
 
-#ifdef __KERNEL_METAL__
+#if defined(__KERNEL_METAL_APPLE__) && defined(__METALRT__)
     KernelGlobals kg = NULL;
     /* Workaround Ambient Occlusion and Bevel nodes not working with Metal.
      * Dummy offset should not affect result, but somehow fixes bug! */