Cycles: Apple Silicon optimization to specialize intersection kernels

The Metal backend now compiles and caches a second set of kernels which are
optimized for scene contents, enabled for Apple Silicon.

The implementation supports doing this both for intersection and shading
kernels. However this is currently only enabled for intersection kernels that
are quick to compile, and already give a good speedup. Enabling this for
shading kernels would be faster still, however this also causes a long wait
times and would need a good user interface to control this.

M1 Max samples per minute (macOS 13.0):

                    PSO_GENERIC  PSO_SPECIALIZED_INTERSECT  PSO_SPECIALIZED_SHADE

barbershop_interior       83.4	            89.5                   93.7
bmw27                   1486.1	          1671.0                 1825.8
classroom                175.2	           196.8                  206.3
fishy_cat                674.2	           704.3                  719.3
junkshop                 205.4	           212.0                  257.7
koro                     310.1	           336.1                  342.8
monster                  376.7	           418.6                  424.1
pabellon                 273.5	           325.4                  339.8
sponza                   830.6	           929.6                 1142.4
victor                    86.7              96.4                   96.3
wdas_cloud               111.8	           112.7                  183.1

Code contributed by Jason Fielder, Morteza Mostajabodaveh and Michael Jones

Differential Revision: https://developer.blender.org/D14645

5 files changed, 31 insertions, 2 deletions

diff --git a/intern/cycles/kernel/CMakeLists.txt b/intern/cycles/kernel/CMakeLists.txt
index 527cc4ec111..21a78722c0d 100644
--- a/intern/cycles/kernel/CMakeLists.txt
+++ b/intern/cycles/kernel/CMakeLists.txt
@@ -79,6 +79,7 @@ set(SRC_KERNEL_DEVICE_METAL_HEADERS
   device/metal/compat.h
   device/metal/context_begin.h
   device/metal/context_end.h
+  device/metal/function_constants.h
   device/metal/globals.h
 )
 
diff --git a/intern/cycles/kernel/device/metal/function_constants.h b/intern/cycles/kernel/device/metal/function_constants.h
new file mode 100644
index 00000000000..f4001735672
--- /dev/null
+++ b/intern/cycles/kernel/device/metal/function_constants.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: Apache-2.0
+ * Copyright 2021-2022 Blender Foundation */
+
+enum {
+#define KERNEL_STRUCT_MEMBER(parent, type, name) KernelData_##parent##_##name,
+#include "kernel/data_template.h"
+};
+
+#ifdef __KERNEL_METAL__
+#  define KERNEL_STRUCT_MEMBER(parent, type, name) \
+    constant type kernel_data_##parent##_##name \
+        [[function_constant(KernelData_##parent##_##name)]];
+#  include "kernel/data_template.h"
+#endif
diff --git a/intern/cycles/kernel/device/metal/kernel.metal b/intern/cycles/kernel/device/metal/kernel.metal
index 3c31dc3354c..74b4b079a32 100644
--- a/intern/cycles/kernel/device/metal/kernel.metal
+++ b/intern/cycles/kernel/device/metal/kernel.metal
@@ -5,6 +5,7 @@
 
 #include "kernel/device/metal/compat.h"
 #include "kernel/device/metal/globals.h"
+#include "kernel/device/metal/function_constants.h"
 #include "kernel/device/gpu/kernel.h"
 
 /* MetalRT intersection handlers */
diff --git a/intern/cycles/kernel/svm/svm.h b/intern/cycles/kernel/svm/svm.h
index 9840cda3655..9d6d3e9222c 100644
--- a/intern/cycles/kernel/svm/svm.h
+++ b/intern/cycles/kernel/svm/svm.h
@@ -204,7 +204,14 @@ CCL_NAMESPACE_END
 
 CCL_NAMESPACE_BEGIN
 
-#define SVM_CASE(node) case node:
+#ifdef __KERNEL_USE_DATA_CONSTANTS__
+#  define SVM_CASE(node) \
+    case node: \
+      if (!kernel_data_svm_usage_##node) \
+        break;
+#else
+#  define SVM_CASE(node) case node:
+#endif
 
 /* Main Interpreter Loop */
 template<uint node_feature_mask, ShaderType type, typename ConstIntegratorGenericState>
diff --git a/intern/cycles/kernel/types.h b/intern/cycles/kernel/types.h
index 72cee6ae344..62ac75e5e4d 100644
--- a/intern/cycles/kernel/types.h
+++ b/intern/cycles/kernel/types.h
@@ -1136,7 +1136,13 @@ typedef enum KernelBVHLayout {
   } \
   ; \
   static_assert_align(name, 16);
-#define KERNEL_STRUCT_MEMBER(parent, type, name) type name;
+
+#ifdef __KERNEL_USE_DATA_CONSTANTS__
+#  define KERNEL_STRUCT_MEMBER(parent, type, name) type __unused_##name;
+#else
+#  define KERNEL_STRUCT_MEMBER(parent, type, name) type name;
+#endif
+
 #include "kernel/data_template.h"
 
 typedef struct KernelTables {