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, 23 insertions, 18 deletions

diff --git a/intern/cycles/kernel/closure/bsdf_principled_diffuse.h b/intern/cycles/kernel/closure/bsdf_principled_diffuse.h
index 52a37eafd9f..6d25daa2356 100644
--- a/intern/cycles/kernel/closure/bsdf_principled_diffuse.h
+++ b/intern/cycles/kernel/closure/bsdf_principled_diffuse.h
@@ -36,7 +36,7 @@ enum PrincipledDiffuseBsdfComponents {
   PRINCIPLED_DIFFUSE_RETRO_REFLECTION = 8,
 };
 
-typedef ccl_addr_space struct PrincipledDiffuseBsdf {
+typedef struct PrincipledDiffuseBsdf {
   SHADER_CLOSURE_BASE;
 
   float roughness;
@@ -46,14 +46,18 @@ typedef ccl_addr_space struct PrincipledDiffuseBsdf {
 static_assert(sizeof(ShaderClosure) >= sizeof(PrincipledDiffuseBsdf),
               "PrincipledDiffuseBsdf is too large!");
 
-ccl_device int bsdf_principled_diffuse_setup(PrincipledDiffuseBsdf *bsdf)
+ccl_device int bsdf_principled_diffuse_setup(ccl_private PrincipledDiffuseBsdf *bsdf)
 {
   bsdf->type = CLOSURE_BSDF_PRINCIPLED_DIFFUSE_ID;
   return SD_BSDF | SD_BSDF_HAS_EVAL;
 }
 
-ccl_device float3 bsdf_principled_diffuse_compute_brdf(
-    const PrincipledDiffuseBsdf *bsdf, float3 N, float3 V, float3 L, float *pdf)
+ccl_device float3
+bsdf_principled_diffuse_compute_brdf(ccl_private const PrincipledDiffuseBsdf *bsdf,
+                                     float3 N,
+                                     float3 V,
+                                     float3 L,
+                                     ccl_private float *pdf)
 {
   const float NdotL = dot(N, L);
 
@@ -102,24 +106,25 @@ ccl_device_inline float bsdf_principled_diffuse_compute_entry_fresnel(const floa
 /* Ad-hoc weight adjustment to avoid retro-reflection taking away half the
  * samples from BSSRDF. */
 ccl_device_inline float bsdf_principled_diffuse_retro_reflection_sample_weight(
-    PrincipledDiffuseBsdf *bsdf, const float3 I)
+    ccl_private PrincipledDiffuseBsdf *bsdf, const float3 I)
 {
   return bsdf->roughness * schlick_fresnel(dot(bsdf->N, I));
 }
 
-ccl_device int bsdf_principled_diffuse_setup(PrincipledDiffuseBsdf *bsdf, int components)
+ccl_device int bsdf_principled_diffuse_setup(ccl_private PrincipledDiffuseBsdf *bsdf,
+                                             int components)
 {
   bsdf->type = CLOSURE_BSDF_PRINCIPLED_DIFFUSE_ID;
   bsdf->components = components;
   return SD_BSDF | SD_BSDF_HAS_EVAL;
 }
 
-ccl_device float3 bsdf_principled_diffuse_eval_reflect(const ShaderClosure *sc,
+ccl_device float3 bsdf_principled_diffuse_eval_reflect(ccl_private const ShaderClosure *sc,
                                                        const float3 I,
                                                        const float3 omega_in,
-                                                       float *pdf)
+                                                       ccl_private float *pdf)
 {
-  const PrincipledDiffuseBsdf *bsdf = (const PrincipledDiffuseBsdf *)sc;
+  ccl_private const PrincipledDiffuseBsdf *bsdf = (ccl_private const PrincipledDiffuseBsdf *)sc;
 
   float3 N = bsdf->N;
   float3 V = I;         // outgoing
@@ -135,28 +140,28 @@ ccl_device float3 bsdf_principled_diffuse_eval_reflect(const ShaderClosure *sc,
   }
 }
 
-ccl_device float3 bsdf_principled_diffuse_eval_transmit(const ShaderClosure *sc,
+ccl_device float3 bsdf_principled_diffuse_eval_transmit(ccl_private const ShaderClosure *sc,
                                                         const float3 I,
                                                         const float3 omega_in,
-                                                        float *pdf)
+                                                        ccl_private float *pdf)
 {
   return make_float3(0.0f, 0.0f, 0.0f);
 }
 
-ccl_device int bsdf_principled_diffuse_sample(const ShaderClosure *sc,
+ccl_device int bsdf_principled_diffuse_sample(ccl_private const ShaderClosure *sc,
                                               float3 Ng,
                                               float3 I,
                                               float3 dIdx,
                                               float3 dIdy,
                                               float randu,
                                               float randv,
-                                              float3 *eval,
-                                              float3 *omega_in,
-                                              float3 *domega_in_dx,
-                                              float3 *domega_in_dy,
-                                              float *pdf)
+                                              ccl_private float3 *eval,
+                                              ccl_private float3 *omega_in,
+                                              ccl_private float3 *domega_in_dx,
+                                              ccl_private float3 *domega_in_dy,
+                                              ccl_private float *pdf)
 {
-  const PrincipledDiffuseBsdf *bsdf = (const PrincipledDiffuseBsdf *)sc;
+  ccl_private const PrincipledDiffuseBsdf *bsdf = (ccl_private const PrincipledDiffuseBsdf *)sc;
 
   float3 N = bsdf->N;