mirror of
https://github.com/encounter/dawn-cmake.git
synced 2025-06-05 14:13:39 +00:00
4d3af66bbd
In order to preserve padding properly for MSL, we need to use its packed_vec type for all vec3 types in storage buffers, not just struct members. This commit includes a complete rewrite of the PackedVec3 transform to achieve this. The key details are: * An internal `__packed_vec3<>` type was added, which corresponds to a `type::Vector` with an additional flag to indicate that it will be emitted as packed vector. * The `PackedVec3` transform replaces all vec3 types used in host-shareable address spaces with the internal `__packed_vec3` type. This includes vec3 types that appear as the store type of a pointer. * When used as an array element, these `__packed_vec3` types are wrapped in a struct that contains a single `__packed_vec3` member. This allows us to add an `@align()` attribute that ensures that `array<vec3<T>>` still has the correct array element stride. * When the `vec3<T>` appears as a struct member in the input program, we apply the `@align()` to that member to ensure that we do not change its offset. * Matrix types with three rows that are used in memory are replaced with an array of columns, where each column uses a `__packed_vec3` inside an aligned wrapper structure as above. * Accesses to host-shareable memory that involve any of these types invoke a "pack" or "unpack" helper function to convert them to the equivalent type that uses `__packed_vec3` or a regular `vec3` as required. * The `chromium_internal_relaxed_uniform_layout` extension is used to avoid issues where modifying a type in the uniform address space triggers stricter layout validation rules. Bug: tint:1571 Fixed: tint:1837 Change-Id: Idaf2da2f5bcb2be00c85ec657edfb614186476bb Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/121200 Reviewed-by: Ben Clayton <bclayton@google.com> Commit-Queue: James Price <jrprice@google.com> Kokoro: Kokoro <noreply+kokoro@google.com>
46 lines
1.5 KiB
Plaintext
46 lines
1.5 KiB
Plaintext
#include <metal_stdlib>
|
|
|
|
using namespace metal;
|
|
|
|
template<typename T, size_t N>
|
|
struct tint_array {
|
|
const constant T& operator[](size_t i) const constant { return elements[i]; }
|
|
device T& operator[](size_t i) device { return elements[i]; }
|
|
const device T& operator[](size_t i) const device { return elements[i]; }
|
|
thread T& operator[](size_t i) thread { return elements[i]; }
|
|
const thread T& operator[](size_t i) const thread { return elements[i]; }
|
|
threadgroup T& operator[](size_t i) threadgroup { return elements[i]; }
|
|
const threadgroup T& operator[](size_t i) const threadgroup { return elements[i]; }
|
|
T elements[N];
|
|
};
|
|
|
|
struct tint_packed_vec3_f16_array_element {
|
|
/* 0x0000 */ packed_half3 elements;
|
|
/* 0x0006 */ tint_array<int8_t, 2> tint_pad;
|
|
};
|
|
|
|
struct S_tint_packed_vec3 {
|
|
/* 0x0000 */ tint_array<tint_packed_vec3_f16_array_element, 4> tint_symbol;
|
|
/* 0x0020 */ packed_half3 vector;
|
|
/* 0x0026 */ tint_array<int8_t, 2> tint_pad_1;
|
|
};
|
|
|
|
half4x3 tint_unpack_vec3_in_composite(tint_array<tint_packed_vec3_f16_array_element, 4> in) {
|
|
half4x3 result = half4x3(0.0h);
|
|
for(uint i = 0u; (i < 4u); i = (i + 1u)) {
|
|
result[i] = half3(in[i].elements);
|
|
}
|
|
return result;
|
|
}
|
|
|
|
struct S {
|
|
half4x3 tint_symbol;
|
|
half3 vector;
|
|
};
|
|
|
|
fragment void tint_symbol_1(const constant S_tint_packed_vec3* tint_symbol_2 [[buffer(0)]]) {
|
|
half4 const x = (half3((*(tint_symbol_2)).vector) * tint_unpack_vec3_in_composite((*(tint_symbol_2)).tint_symbol));
|
|
return;
|
|
}
|
|
|