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, 24 insertions, 19 deletions

diff --git a/intern/cycles/kernel/closure/bsdf_ashikhmin_shirley.h b/intern/cycles/kernel/closure/bsdf_ashikhmin_shirley.h
index be6383e521a..6cd8739ce39 100644
--- a/intern/cycles/kernel/closure/bsdf_ashikhmin_shirley.h
+++ b/intern/cycles/kernel/closure/bsdf_ashikhmin_shirley.h
@@ -30,7 +30,7 @@
 
 CCL_NAMESPACE_BEGIN
 
-ccl_device int bsdf_ashikhmin_shirley_setup(MicrofacetBsdf *bsdf)
+ccl_device int bsdf_ashikhmin_shirley_setup(ccl_private MicrofacetBsdf *bsdf)
 {
   bsdf->alpha_x = clamp(bsdf->alpha_x, 1e-4f, 1.0f);
   bsdf->alpha_y = clamp(bsdf->alpha_y, 1e-4f, 1.0f);
@@ -39,9 +39,9 @@ ccl_device int bsdf_ashikhmin_shirley_setup(MicrofacetBsdf *bsdf)
   return SD_BSDF | SD_BSDF_HAS_EVAL;
 }
 
-ccl_device void bsdf_ashikhmin_shirley_blur(ShaderClosure *sc, float roughness)
+ccl_device void bsdf_ashikhmin_shirley_blur(ccl_private ShaderClosure *sc, float roughness)
 {
-  MicrofacetBsdf *bsdf = (MicrofacetBsdf *)sc;
+  ccl_private MicrofacetBsdf *bsdf = (ccl_private MicrofacetBsdf *)sc;
 
   bsdf->alpha_x = fmaxf(roughness, bsdf->alpha_x);
   bsdf->alpha_y = fmaxf(roughness, bsdf->alpha_y);
@@ -52,12 +52,13 @@ ccl_device_inline float bsdf_ashikhmin_shirley_roughness_to_exponent(float rough
   return 2.0f / (roughness * roughness) - 2.0f;
 }
 
-ccl_device_forceinline float3 bsdf_ashikhmin_shirley_eval_reflect(const ShaderClosure *sc,
-                                                                  const float3 I,
-                                                                  const float3 omega_in,
-                                                                  float *pdf)
+ccl_device_forceinline float3
+bsdf_ashikhmin_shirley_eval_reflect(ccl_private const ShaderClosure *sc,
+                                    const float3 I,
+                                    const float3 omega_in,
+                                    ccl_private float *pdf)
 {
-  const MicrofacetBsdf *bsdf = (const MicrofacetBsdf *)sc;
+  ccl_private const MicrofacetBsdf *bsdf = (ccl_private const MicrofacetBsdf *)sc;
   float3 N = bsdf->N;
 
   float NdotI = dot(N, I);        /* in Cycles/OSL convention I is omega_out */
@@ -119,16 +120,20 @@ ccl_device_forceinline float3 bsdf_ashikhmin_shirley_eval_reflect(const ShaderCl
   return make_float3(out, out, out);
 }
 
-ccl_device float3 bsdf_ashikhmin_shirley_eval_transmit(const ShaderClosure *sc,
+ccl_device float3 bsdf_ashikhmin_shirley_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_inline void bsdf_ashikhmin_shirley_sample_first_quadrant(
-    float n_x, float n_y, float randu, float randv, float *phi, float *cos_theta)
+ccl_device_inline void bsdf_ashikhmin_shirley_sample_first_quadrant(float n_x,
+                                                                    float n_y,
+                                                                    float randu,
+                                                                    float randv,
+                                                                    ccl_private float *phi,
+                                                                    ccl_private float *cos_theta)
 {
   *phi = atanf(sqrtf((n_x + 1.0f) / (n_y + 1.0f)) * tanf(M_PI_2_F * randu));
   float cos_phi = cosf(*phi);
@@ -136,20 +141,20 @@ ccl_device_inline void bsdf_ashikhmin_shirley_sample_first_quadrant(
   *cos_theta = powf(randv, 1.0f / (n_x * cos_phi * cos_phi + n_y * sin_phi * sin_phi + 1.0f));
 }
 
-ccl_device int bsdf_ashikhmin_shirley_sample(const ShaderClosure *sc,
+ccl_device int bsdf_ashikhmin_shirley_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 MicrofacetBsdf *bsdf = (const MicrofacetBsdf *)sc;
+  ccl_private const MicrofacetBsdf *bsdf = (ccl_private const MicrofacetBsdf *)sc;
   float3 N = bsdf->N;
   int label = LABEL_REFLECT | LABEL_GLOSSY;