dawn-cmake/test/tint/samples/compute_boids.wgsl.expected...

136 lines
4.4 KiB
Plaintext
Raw Normal View History

#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_symbol_1 {
float2 a_particlePos [[attribute(0)]];
float2 a_particleVel [[attribute(1)]];
float2 a_pos [[attribute(2)]];
};
struct tint_symbol_2 {
float4 value [[position]];
};
float4 vert_main_inner(float2 a_particlePos, float2 a_particleVel, float2 a_pos) {
float angle = -(atan2(a_particleVel[0], a_particleVel[1]));
float2 pos = float2(((a_pos[0] * cos(angle)) - (a_pos[1] * sin(angle))), ((a_pos[0] * sin(angle)) + (a_pos[1] * cos(angle))));
return float4((pos + a_particlePos), 0.0f, 1.0f);
}
vertex tint_symbol_2 vert_main(tint_symbol_1 tint_symbol [[stage_in]]) {
float4 const inner_result = vert_main_inner(tint_symbol.a_particlePos, tint_symbol.a_particleVel, tint_symbol.a_pos);
tint_symbol_2 wrapper_result = {};
wrapper_result.value = inner_result;
return wrapper_result;
}
struct tint_symbol_3 {
float4 value [[color(0)]];
};
float4 frag_main_inner() {
return float4(1.0f);
}
fragment tint_symbol_3 frag_main() {
float4 const inner_result_1 = frag_main_inner();
tint_symbol_3 wrapper_result_1 = {};
wrapper_result_1.value = inner_result_1;
return wrapper_result_1;
}
struct Particle {
/* 0x0000 */ float2 pos;
/* 0x0008 */ float2 vel;
};
struct SimParams {
/* 0x0000 */ float deltaT;
/* 0x0004 */ float rule1Distance;
/* 0x0008 */ float rule2Distance;
/* 0x000c */ float rule3Distance;
/* 0x0010 */ float rule1Scale;
/* 0x0014 */ float rule2Scale;
/* 0x0018 */ float rule3Scale;
};
struct Particles {
/* 0x0000 */ tint_array<Particle, 5> particles;
};
void comp_main_inner(uint3 gl_GlobalInvocationID, device Particles* const tint_symbol_4, const constant SimParams* const tint_symbol_5, device Particles* const tint_symbol_6) {
uint index = gl_GlobalInvocationID[0];
if ((index >= 5u)) {
return;
}
float2 vPos = (*(tint_symbol_4)).particles[index].pos;
float2 vVel = (*(tint_symbol_4)).particles[index].vel;
float2 cMass = float2(0.0f);
float2 cVel = float2(0.0f);
float2 colVel = float2(0.0f);
int cMassCount = 0;
int cVelCount = 0;
float2 pos = 0.0f;
float2 vel = 0.0f;
for(uint i = 0u; (i < 5u); i = (i + 1u)) {
if ((i == index)) {
continue;
}
tint/msl: Preserve trailing vec3 padding 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>
2023-02-27 20:21:03 +00:00
pos = (*(tint_symbol_4)).particles[i].pos.xy;
vel = (*(tint_symbol_4)).particles[i].vel.xy;
if ((distance(pos, vPos) < (*(tint_symbol_5)).rule1Distance)) {
cMass = (cMass + pos);
cMassCount = as_type<int>((as_type<uint>(cMassCount) + as_type<uint>(1)));
}
if ((distance(pos, vPos) < (*(tint_symbol_5)).rule2Distance)) {
colVel = (colVel - (pos - vPos));
}
if ((distance(pos, vPos) < (*(tint_symbol_5)).rule3Distance)) {
cVel = (cVel + vel);
cVelCount = as_type<int>((as_type<uint>(cVelCount) + as_type<uint>(1)));
}
}
if ((cMassCount > 0)) {
cMass = ((cMass / float2(float(cMassCount), float(cMassCount))) - vPos);
}
if ((cVelCount > 0)) {
cVel = (cVel / float2(float(cVelCount), float(cVelCount)));
}
vVel = (((vVel + (cMass * (*(tint_symbol_5)).rule1Scale)) + (colVel * (*(tint_symbol_5)).rule2Scale)) + (cVel * (*(tint_symbol_5)).rule3Scale));
vVel = (normalize(vVel) * clamp(length(vVel), 0.0f, 0.100000001f));
vPos = (vPos + (vVel * (*(tint_symbol_5)).deltaT));
if ((vPos[0] < -1.0f)) {
vPos[0] = 1.0f;
}
if ((vPos[0] > 1.0f)) {
vPos[0] = -1.0f;
}
if ((vPos[1] < -1.0f)) {
vPos[1] = 1.0f;
}
if ((vPos[1] > 1.0f)) {
vPos[1] = -1.0f;
}
(*(tint_symbol_6)).particles[index].pos = vPos;
(*(tint_symbol_6)).particles[index].vel = vVel;
}
kernel void comp_main(device Particles* tint_symbol_7 [[buffer(1)]], const constant SimParams* tint_symbol_8 [[buffer(0)]], device Particles* tint_symbol_9 [[buffer(2)]], uint3 gl_GlobalInvocationID [[thread_position_in_grid]]) {
comp_main_inner(gl_GlobalInvocationID, tint_symbol_7, tint_symbol_8, tint_symbol_9);
return;
}