mirror of
https://github.com/libretro/RetroArch
synced 2025-01-17 01:16:25 +00:00
695837ef77
8aa6731925 Merge pull request #1065 from KhronosGroup/msvc-2013-workaround 909040e2eb MSVC 2013: Work around another compiler bug with array init. 53ab2144b9 Merge pull request #1064 from KhronosGroup/fix-1062 e0cd8595a4 Merge pull request #1063 from KhronosGroup/fix-1061 50342966c0 Fall back to complex loop if non-trivial continue block is found. fa9af7223a Add test shaders for NonUniformEXT propagation. d12b54bbb4 Propagate NonUniformEXT to dependent expressions. 13378ad1ac Add simple test for extended debug operations. 6d9c502a3a Merge branch 'master' of git://github.com/lifpan/SPIRV-Cross 5ca8779044 Parse SPIR-V debug information extended instructions, as well as OpNoLine. c5904dd245 Merge pull request #1059 from KhronosGroup/fix-1056 4056d0b74e Don't use scalar dot(). 041f103d44 MSL/HLSL: Support scalar reflect and refract. 9a6e2534e9 Merge pull request #1058 from KhronosGroup/fix-1054 fc9fe4e480 Fix variable scope when an if or else block dominates a variable. 3af18e741f Merge pull request #1055 from cdavis5e/msl21-frag-subgroup-builtins 31b6c93516 MSL: Support SubgroupLocalInvocationId and SubgroupSize in all stages. 41399fc899 Merge pull request #1051 from KhronosGroup/fix-1049 f8b084de61 MSL/HLSL: Support OpOuterProduct. 04e29895a3 Merge pull request #1001 from cdavis5e/msl-multiview 7eecf5a46b MSL: Support SPV_KHR_multiview. 8ee8e60f70 Merge pull request #1048 from KhronosGroup/fix-1047 ff87419607 Deal with scalar input values for distance/length/normalize. d1bdb6d491 Merge pull request #1046 from KhronosGroup/texture-fp16-coord 964ec44822 Merge pull request #1045 from KhronosGroup/c-api-get-declared-struct-member-size 1543bdaf7b Run format_all.sh. 581ed0fd59 HLSL: Does not support case-fallthrough. c76b99b711 Handle more cases with FP16 and texture sampling. 656d129c00 Add C API for get_declared_struct_member_size. 45805857e5 MSL: De-virtualize get_declared_struct_member_size. 02b2a1015d MSL: Fix minor XCode /analyze warning. 8f6939cb0d Merge pull request #1041 from KhronosGroup/fix-1011 4bbf343a7f Merge pull request #1043 from KhronosGroup/fix-1042 bcef66fbf3 Fix declaration of loop variables with a Phi helper copy. 845628cd4e Merge pull request #1040 from KhronosGroup/fix-1037 ab3798fd91 MSL: Add support for SubgroupSize / SubgroupInvocationID in fragment. 048f2380f3 MSL: Support custom bindings for argument buffer itself. git-subtree-dir: deps/SPIRV-Cross git-subtree-split: 8aa67319253b55f874d1fc7eb85d201299a8f488
120 lines
4.3 KiB
GLSL
120 lines
4.3 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);
|
|
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);
|
|
}
|