SPIRV-Cross-Vulnerable/shaders-msl-no-opt/frag/subgroups.nocompat.invalid.vk.msl22.frag
Chip Davis 68908355a9 MSL: Expand subgroup support.
Add support for declaring a fixed subgroup size. Metal, like Vulkan with
`VK_EXT_subgroup_size_control`, allows the thread execution width to
vary depending on factors such as register usage. Unfortunately, this
breaks several tests that depend on the subgroup size being what the
device says it is. So we'll fix the subgroup size at the size the device
declares. The extra invocations in the subgroup will appear to be
inactive. Because of this, the ballot mask builtins are now ANDed with
the active subgroup mask.

Add support for emulating a subgroup of size 1. This is intended to be
used by Vulkan Portability implementations (e.g. MoltenVK) when the
hardware/software combo provides insufficient support for subgroups.
Luckily for us, Vulkan 1.1 only requires that the subgroup size be at
least 1.

Add support for quadgroup and SIMD-group functions which were added to
iOS in Metal 2.2 and 2.3. This will allow clients to take advantage of
expanded quadgroup and SIMD-group support in recent Metal versions and
on recent Apple GPUs (families 6 and 7).

Gut emulation of subgroup builtins in fragment shaders. It turns out
codegen for the SIMD-group functions in fragment wasn't implemented for
AMD on Mojave; it's a safe bet that it wasn't implemented for the other
drivers either. Subgroup support in fragment shaders now requires Metal
2.2.
2020-11-20 15:55:49 -06:00

132 lines
5.0 KiB
GLSL

#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(location = 0) out float FragColor;
void main()
{
// basic
FragColor = float(gl_SubgroupSize);
FragColor = float(gl_SubgroupInvocationID);
subgroupBarrier();
subgroupMemoryBarrier();
subgroupMemoryBarrierBuffer();
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);
bvec2 broadcasted_bool = subgroupBroadcast(bvec2(true), 8u);
vec3 first = subgroupBroadcastFirst(vec3(20.0));
bvec4 first_bool = subgroupBroadcastFirst(bvec4(false));
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);
bool shuffled_bool = subgroupShuffle(true, 9u);
uint shuffled_xor = subgroupShuffleXor(30u, 8u);
bool shuffled_xor_bool = subgroupShuffleXor(false, 9u);
// shuffle relative
uint shuffled_up = subgroupShuffleUp(20u, 4u);
bool shuffled_up_bool = subgroupShuffleUp(true, 4u);
uint shuffled_down = subgroupShuffleDown(20u, 4u);
bool shuffled_down_bool = subgroupShuffleDown(false, 4u);
// vote
bool has_all = subgroupAll(true);
bool has_any = subgroupAny(true);
bool has_equal = subgroupAllEqual(0);
has_equal = subgroupAllEqual(true);
has_equal = subgroupAllEqual(vec3(0.0, 1.0, 2.0));
has_equal = subgroupAllEqual(bvec4(true, true, false, 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));
bvec4 swap_horiz_bool = subgroupQuadSwapHorizontal(bvec4(true));
vec4 swap_vertical = subgroupQuadSwapVertical(vec4(20.0));
bvec4 swap_vertical_bool = subgroupQuadSwapVertical(bvec4(true));
vec4 swap_diagonal = subgroupQuadSwapDiagonal(vec4(20.0));
bvec4 swap_diagonal_bool = subgroupQuadSwapDiagonal(bvec4(true));
vec4 quad_broadcast = subgroupQuadBroadcast(vec4(20.0), 3u);
bvec4 quad_broadcast_bool = subgroupQuadBroadcast(bvec4(true), 3u);
}