MSL: Add support for processing more than one patch per workgroup.

This should hopefully reduce underutilization of the GPU, especially on
GPUs where the thread execution width is greater than the number of
control points.

This also simplifies initialization by reading the buffer directly
instead of using Metal's vertex-attribute-in-compute support. It turns
out the only way in which shader stages are allowed to differ in their
interfaces is in the number of components per vector; the base type must
be the same. Since we are using the raw buffer instead of attributes, we
can now also emit arrays and matrices directly into the buffer, instead
of flattening them and then unpacking them. Structs are still flattened,
however; this is due to the need to handle vectors with fewer components
than were output, and I think handling this while also directly emitting
structs could get ugly.

Another advantage of this scheme is that the extra invocations needed to
read the attributes when there were more input than output points are
now no more. The number of threads per workgroup is now lcm(SIMD-size,
output control points). This should ensure we always process a whole
number of patches per workgroup.

To avoid complexity handling indices in the tessellation control shader,
I've also changed the way vertex shaders for tessellation are handled.
They are now compute kernels using Metal's support for vertex-style
stage input. This lets us always emit vertices into the buffer in order
of vertex shader execution. Now we no longer have to deal with indexing
in the tessellation control shader. This also fixes a long-standing
issue where if an index were greater than the number of vertices to
draw, the vertex shader would wind up writing outside the buffer, and
the vertex would be lost.

This is a breaking change, and I know SPIRV-Cross has other clients, so
I've hidden this behind an option for now. In the future, I want to
remove this option and make it the default.

1 files changed, 18 insertions, 1 deletions

diff --git a/spirv_cross_c.h b/spirv_cross_c.h
index 082c83b8..0ea8bf69 100644
--- a/spirv_cross_c.h
+++ b/spirv_cross_c.h
@@ -33,7 +33,7 @@ extern "C" {
 /* Bumped if ABI or API breaks backwards compatibility. */
 #define SPVC_C_API_VERSION_MAJOR 0
 /* Bumped if APIs or enumerations are added in a backwards compatible way. */
-#define SPVC_C_API_VERSION_MINOR 35
+#define SPVC_C_API_VERSION_MINOR 36
 /* Bumped if internal implementation details change. */
 #define SPVC_C_API_VERSION_PATCH 0
 
@@ -259,11 +259,22 @@ typedef enum spvc_msl_platform
 } spvc_msl_platform;
 
 /* Maps to C++ API. */
+typedef enum spvc_msl_index_type
+{
+	SPVC_MSL_INDEX_TYPE_NONE = 0,
+	SPVC_MSL_INDEX_TYPE_UINT16 = 1,
+	SPVC_MSL_INDEX_TYPE_UINT32 = 2,
+	SPVC_MSL_INDEX_TYPE_MAX_INT = 0x7fffffff
+} spvc_msl_index_type;
+
+/* Maps to C++ API. */
 typedef enum spvc_msl_shader_input_format
 {
 	SPVC_MSL_SHADER_INPUT_FORMAT_OTHER = 0,
 	SPVC_MSL_SHADER_INPUT_FORMAT_UINT8 = 1,
 	SPVC_MSL_SHADER_INPUT_FORMAT_UINT16 = 2,
+	SPVC_MSL_SHADER_INPUT_FORMAT_ANY16 = 3,
+	SPVC_MSL_SHADER_INPUT_FORMAT_ANY32 = 4,
 
 	/* Deprecated names. */
 	SPVC_MSL_VERTEX_FORMAT_OTHER = SPVC_MSL_SHADER_INPUT_FORMAT_OTHER,
@@ -617,6 +628,12 @@ typedef enum spvc_compiler_option
 
 	SPVC_COMPILER_OPTION_HLSL_ENABLE_16BIT_TYPES = 60 | SPVC_COMPILER_OPTION_HLSL_BIT,
 
+	SPVC_COMPILER_OPTION_MSL_MULTI_PATCH_WORKGROUP = 61 | SPVC_COMPILER_OPTION_MSL_BIT,
+	SPVC_COMPILER_OPTION_MSL_SHADER_INPUT_BUFFER_INDEX = 62 | SPVC_COMPILER_OPTION_MSL_BIT,
+	SPVC_COMPILER_OPTION_MSL_SHADER_INDEX_BUFFER_INDEX = 63 | SPVC_COMPILER_OPTION_MSL_BIT,
+	SPVC_COMPILER_OPTION_MSL_VERTEX_FOR_TESSELLATION = 64 | SPVC_COMPILER_OPTION_MSL_BIT,
+	SPVC_COMPILER_OPTION_MSL_VERTEX_INDEX_TYPE = 65 | SPVC_COMPILER_OPTION_MSL_BIT,
+
 	SPVC_COMPILER_OPTION_INT_MAX = 0x7fffffff
 } spvc_compiler_option;