9d9415754b
Some support for subgroups is present starting in Metal 2.0 on both iOS and macOS. macOS gains more complete support in 10.14 (Metal 2.1). Some restrictions are present. On iOS and on macOS 10.13, the implementation of `OpGroupNonUniformElect` is incorrect: if thread 0 has already terminated or is not executing a conditional branch, the first thread that *is* will falsely believe itself not to be. Unfortunately, this operation is part of the "basic" feature set; without it, subgroups cannot be supported at all. The `SubgroupSize` and `SubgroupLocalInvocationId` builtins are only available in compute shaders (and, by extension, tessellation control shaders), despite SPIR-V making them available in all stages. This limits the usefulness of some of the subgroup operations in fragment shaders. Although Metal on macOS supports some clustered, inclusive, and exclusive operations, it does not support them all. In particular, inclusive and exclusive min, max, and, or, and xor; as well as cluster sizes other than 4 are not supported. If this becomes a problem, they could be emulated, but at a significant performance cost due to the need for non-uniform operations.
127 lines
4.4 KiB
Plaintext
127 lines
4.4 KiB
Plaintext
#version 450
|
|
#extension GL_KHR_shader_subgroup_basic : require
|
|
#extension GL_KHR_shader_subgroup_ballot : require
|
|
#extension GL_KHR_shader_subgroup_vote : require
|
|
#extension GL_KHR_shader_subgroup_shuffle : require
|
|
#extension GL_KHR_shader_subgroup_shuffle_relative : require
|
|
#extension GL_KHR_shader_subgroup_arithmetic : require
|
|
#extension GL_KHR_shader_subgroup_clustered : require
|
|
#extension GL_KHR_shader_subgroup_quad : require
|
|
layout(local_size_x = 1) in;
|
|
|
|
layout(std430, binding = 0) buffer SSBO
|
|
{
|
|
float FragColor;
|
|
};
|
|
|
|
void main()
|
|
{
|
|
// basic
|
|
FragColor = float(gl_NumSubgroups);
|
|
FragColor = float(gl_SubgroupID);
|
|
FragColor = float(gl_SubgroupSize);
|
|
FragColor = float(gl_SubgroupInvocationID);
|
|
subgroupBarrier();
|
|
subgroupMemoryBarrier();
|
|
subgroupMemoryBarrierBuffer();
|
|
subgroupMemoryBarrierShared();
|
|
subgroupMemoryBarrierImage();
|
|
bool elected = subgroupElect();
|
|
|
|
// ballot
|
|
FragColor = float(gl_SubgroupEqMask);
|
|
FragColor = float(gl_SubgroupGeMask);
|
|
FragColor = float(gl_SubgroupGtMask);
|
|
FragColor = float(gl_SubgroupLeMask);
|
|
FragColor = float(gl_SubgroupLtMask);
|
|
vec4 broadcasted = subgroupBroadcast(vec4(10.0), 8u);
|
|
vec3 first = subgroupBroadcastFirst(vec3(20.0));
|
|
uvec4 ballot_value = subgroupBallot(true);
|
|
bool inverse_ballot_value = subgroupInverseBallot(ballot_value);
|
|
bool bit_extracted = subgroupBallotBitExtract(uvec4(10u), 8u);
|
|
uint bit_count = subgroupBallotBitCount(ballot_value);
|
|
uint inclusive_bit_count = subgroupBallotInclusiveBitCount(ballot_value);
|
|
uint exclusive_bit_count = subgroupBallotExclusiveBitCount(ballot_value);
|
|
uint lsb = subgroupBallotFindLSB(ballot_value);
|
|
uint msb = subgroupBallotFindMSB(ballot_value);
|
|
|
|
// shuffle
|
|
uint shuffled = subgroupShuffle(10u, 8u);
|
|
uint shuffled_xor = subgroupShuffleXor(30u, 8u);
|
|
|
|
// shuffle relative
|
|
uint shuffled_up = subgroupShuffleUp(20u, 4u);
|
|
uint shuffled_down = subgroupShuffleDown(20u, 4u);
|
|
|
|
// vote
|
|
bool has_all = subgroupAll(true);
|
|
bool has_any = subgroupAny(true);
|
|
bool has_equal = subgroupAllEqual(0);
|
|
has_equal = subgroupAllEqual(true);
|
|
|
|
// arithmetic
|
|
vec4 added = subgroupAdd(vec4(20.0));
|
|
ivec4 iadded = subgroupAdd(ivec4(20));
|
|
vec4 multiplied = subgroupMul(vec4(20.0));
|
|
ivec4 imultiplied = subgroupMul(ivec4(20));
|
|
vec4 lo = subgroupMin(vec4(20.0));
|
|
vec4 hi = subgroupMax(vec4(20.0));
|
|
ivec4 slo = subgroupMin(ivec4(20));
|
|
ivec4 shi = subgroupMax(ivec4(20));
|
|
uvec4 ulo = subgroupMin(uvec4(20));
|
|
uvec4 uhi = subgroupMax(uvec4(20));
|
|
uvec4 anded = subgroupAnd(ballot_value);
|
|
uvec4 ored = subgroupOr(ballot_value);
|
|
uvec4 xored = subgroupXor(ballot_value);
|
|
|
|
added = subgroupInclusiveAdd(added);
|
|
iadded = subgroupInclusiveAdd(iadded);
|
|
multiplied = subgroupInclusiveMul(multiplied);
|
|
imultiplied = subgroupInclusiveMul(imultiplied);
|
|
//lo = subgroupInclusiveMin(lo); // FIXME: Unsupported by Metal
|
|
//hi = subgroupInclusiveMax(hi);
|
|
//slo = subgroupInclusiveMin(slo);
|
|
//shi = subgroupInclusiveMax(shi);
|
|
//ulo = subgroupInclusiveMin(ulo);
|
|
//uhi = subgroupInclusiveMax(uhi);
|
|
//anded = subgroupInclusiveAnd(anded);
|
|
//ored = subgroupInclusiveOr(ored);
|
|
//xored = subgroupInclusiveXor(ored);
|
|
//added = subgroupExclusiveAdd(lo);
|
|
|
|
added = subgroupExclusiveAdd(multiplied);
|
|
multiplied = subgroupExclusiveMul(multiplied);
|
|
iadded = subgroupExclusiveAdd(imultiplied);
|
|
imultiplied = subgroupExclusiveMul(imultiplied);
|
|
//lo = subgroupExclusiveMin(lo); // FIXME: Unsupported by Metal
|
|
//hi = subgroupExclusiveMax(hi);
|
|
//ulo = subgroupExclusiveMin(ulo);
|
|
//uhi = subgroupExclusiveMax(uhi);
|
|
//slo = subgroupExclusiveMin(slo);
|
|
//shi = subgroupExclusiveMax(shi);
|
|
//anded = subgroupExclusiveAnd(anded);
|
|
//ored = subgroupExclusiveOr(ored);
|
|
//xored = subgroupExclusiveXor(ored);
|
|
|
|
// clustered
|
|
added = subgroupClusteredAdd(added, 4u);
|
|
multiplied = subgroupClusteredMul(multiplied, 4u);
|
|
iadded = subgroupClusteredAdd(iadded, 4u);
|
|
imultiplied = subgroupClusteredMul(imultiplied, 4u);
|
|
lo = subgroupClusteredMin(lo, 4u);
|
|
hi = subgroupClusteredMax(hi, 4u);
|
|
ulo = subgroupClusteredMin(ulo, 4u);
|
|
uhi = subgroupClusteredMax(uhi, 4u);
|
|
slo = subgroupClusteredMin(slo, 4u);
|
|
shi = subgroupClusteredMax(shi, 4u);
|
|
anded = subgroupClusteredAnd(anded, 4u);
|
|
ored = subgroupClusteredOr(ored, 4u);
|
|
xored = subgroupClusteredXor(xored, 4u);
|
|
|
|
// quad
|
|
vec4 swap_horiz = subgroupQuadSwapHorizontal(vec4(20.0));
|
|
vec4 swap_vertical = subgroupQuadSwapVertical(vec4(20.0));
|
|
vec4 swap_diagonal = subgroupQuadSwapDiagonal(vec4(20.0));
|
|
vec4 quad_broadcast = subgroupQuadBroadcast(vec4(20.0), 3u);
|
|
}
|