Cycles: Kernel address space changes for MSL

This is the first of a sequence of changes to support compiling Cycles kernels as MSL (Metal Shading Language) in preparation for a Metal GPU device implementation.

MSL requires that all pointer types be declared with explicit address space attributes (device, thread, etc...). There is already precedent for this with Cycles' address space macros (ccl_global, ccl_private, etc...), therefore the first step of MSL-enablement is to apply these consistently. Line-for-line this represents the largest change required to enable MSL. Applying this change first will simplify future patches as well as offering the emergent benefit of enhanced descriptiveness.

The vast majority of deltas in this patch fall into one of two cases:

- Ensuring ccl_private is specified for thread-local pointer types
- Ensuring ccl_global is specified for device-wide pointer types

Additionally, the ccl_addr_space qualifier can be removed. Prior to Cycles X, ccl_addr_space was used as a context-dependent address space qualifier, but now it is either redundant (e.g. in struct typedefs), or can be replaced by ccl_global in the case of pointer types. Associated function variants (e.g. lcg_step_float_addrspace) are also redundant.

In cases where address space qualifiers are chained with "const", this patch places the address space qualifier first. The rationale for this is that the choice of address space is likely to have the greater impact on runtime performance and overall architecture.

The final part of this patch is the addition of a metal/compat.h header. This is partially complete and will be extended in future patches, paving the way for the full Metal implementation.

Ref T92212

Reviewed By: brecht

Maniphest Tasks: T92212

Differential Revision: https://developer.blender.org/D12864

1 files changed, 11 insertions, 11 deletions

diff --git a/intern/cycles/kernel/closure/bsdf_microfacet_multi_impl.h b/intern/cycles/kernel/closure/bsdf_microfacet_multi_impl.h
index 04d9b22d7d2..d23cc16cff3 100644
--- a/intern/cycles/kernel/closure/bsdf_microfacet_multi_impl.h
+++ b/intern/cycles/kernel/closure/bsdf_microfacet_multi_impl.h
@@ -31,7 +31,7 @@ ccl_device_forceinline float3 MF_FUNCTION_FULL_NAME(mf_eval)(float3 wi,
                                                              const float3 color,
                                                              const float alpha_x,
                                                              const float alpha_y,
-                                                             ccl_addr_space uint *lcg_state,
+                                                             ccl_private uint *lcg_state,
                                                              const float eta,
                                                              bool use_fresnel,
                                                              const float3 cspec0)
@@ -101,12 +101,12 @@ ccl_device_forceinline float3 MF_FUNCTION_FULL_NAME(mf_eval)(float3 wi,
 
   for (int order = 0; order < 10; order++) {
     /* Sample microfacet height. */
-    float height_rand = lcg_step_float_addrspace(lcg_state);
+    float height_rand = lcg_step_float(lcg_state);
     if (!mf_sample_height(wr, &hr, &C1_r, &G1_r, &lambda_r, height_rand))
       break;
     /* Sample microfacet normal. */
-    float vndf_rand_y = lcg_step_float_addrspace(lcg_state);
-    float vndf_rand_x = lcg_step_float_addrspace(lcg_state);
+    float vndf_rand_y = lcg_step_float(lcg_state);
+    float vndf_rand_x = lcg_step_float(lcg_state);
     float3 wm = mf_sample_vndf(-wr, alpha, vndf_rand_x, vndf_rand_y);
 
 #ifdef MF_MULTI_GLASS
@@ -145,7 +145,7 @@ ccl_device_forceinline float3 MF_FUNCTION_FULL_NAME(mf_eval)(float3 wi,
 #ifdef MF_MULTI_GLASS
       bool next_outside;
       float3 wi_prev = -wr;
-      float phase_rand = lcg_step_float_addrspace(lcg_state);
+      float phase_rand = lcg_step_float(lcg_state);
       wr = mf_sample_phase_glass(-wr, outside ? eta : 1.0f / eta, wm, phase_rand, &next_outside);
       if (!next_outside) {
         outside = !outside;
@@ -186,11 +186,11 @@ ccl_device_forceinline float3 MF_FUNCTION_FULL_NAME(mf_eval)(float3 wi,
  * reflection losses due to coloring or fresnel absorption in conductors, the sampling is optimal.
  */
 ccl_device_forceinline float3 MF_FUNCTION_FULL_NAME(mf_sample)(float3 wi,
-                                                               float3 *wo,
+                                                               ccl_private float3 *wo,
                                                                const float3 color,
                                                                const float alpha_x,
                                                                const float alpha_y,
-                                                               ccl_addr_space uint *lcg_state,
+                                                               ccl_private uint *lcg_state,
                                                                const float eta,
                                                                bool use_fresnel,
                                                                const float3 cspec0)
@@ -213,15 +213,15 @@ ccl_device_forceinline float3 MF_FUNCTION_FULL_NAME(mf_sample)(float3 wi,
   int order;
   for (order = 0; order < 10; order++) {
     /* Sample microfacet height. */
-    float height_rand = lcg_step_float_addrspace(lcg_state);
+    float height_rand = lcg_step_float(lcg_state);
     if (!mf_sample_height(wr, &hr, &C1_r, &G1_r, &lambda_r, height_rand)) {
       /* The random walk has left the surface. */
       *wo = outside ? wr : -wr;
       return throughput;
     }
     /* Sample microfacet normal. */
-    float vndf_rand_y = lcg_step_float_addrspace(lcg_state);
-    float vndf_rand_x = lcg_step_float_addrspace(lcg_state);
+    float vndf_rand_y = lcg_step_float(lcg_state);
+    float vndf_rand_x = lcg_step_float(lcg_state);
     float3 wm = mf_sample_vndf(-wr, alpha, vndf_rand_x, vndf_rand_y);
 
     /* First-bounce color is already accounted for in mix weight. */
@@ -232,7 +232,7 @@ ccl_device_forceinline float3 MF_FUNCTION_FULL_NAME(mf_sample)(float3 wi,
 #ifdef MF_MULTI_GLASS
     bool next_outside;
     float3 wi_prev = -wr;
-    float phase_rand = lcg_step_float_addrspace(lcg_state);
+    float phase_rand = lcg_step_float(lcg_state);
     wr = mf_sample_phase_glass(-wr, outside ? eta : 1.0f / eta, wm, phase_rand, &next_outside);
     if (!next_outside) {
       hr = -hr;