swung0x48/MobileGL
1
0
Fork 0
mirror of https://github.com/MobileGL-Dev/MobileGL synced 2026-11-07 18:13:23 +09:00
Code Issues Packages Projects Releases Wiki Activity

Magma: the pipeline, program and sampler hashes read their thread_local state once per hash (GetOrCreatePipeline 0.026 -> 0.013 ms/frame).

Browse Source
This commit is contained in:
swung0x48
2026-10-09 07:42:03 -04:00
parent 485dff1421
commit c85c9439a5
3 changed files with 76 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files
MobileGL/MG_Backend/DirectVulkan/Renderer/ProgramFactory.cpp
+13 -11
View File
@@ -2575,26 +2575,28 @@ namespace MobileGL::MG_Backend::DirectVulkan {
ProgramFactory::HashType ProgramFactory::ComputeHash(const MagmaProgramSource& program,
CompileOptionFlags flags) const {
XXHASH_VERIFY(XXH64_reset(m_hashState, m_config.CacheVersion));
// P15: one read of the thread_local per hash (emulated TLS: every read is a call).
XXH64_state_t* const hashState = m_hashState;
XXHASH_VERIFY(XXH64_reset(hashState, m_config.CacheVersion));
// We expect shader stages in program object are sorted
const auto& spirvs = program.GetGeneratedSpirv();
for (const auto& spv : spirvs) {
XXHASH_VERIFY(XXH64_update(m_hashState, spv.data(), spv.size() * sizeof(Uint)));
XXHASH_VERIFY(XXH64_update(hashState, spv.data(), spv.size() * sizeof(Uint)));
}
XXHASH_VERIFY(XXH64_update(m_hashState, &flags, sizeof(CompileOptionFlags)));
XXHASH_VERIFY(XXH64_update(hashState, &flags, sizeof(CompileOptionFlags)));
// Only FragCoordYFlip variants bake the height in, so mixing it unconditionally would
// re-key every program in the cache on a resize for no reason.
if (flags & CompileOptionBit::FragCoordYFlip) {
XXHASH_VERIFY(XXH64_update(m_hashState, &m_defaultFramebufferHeight,
XXHASH_VERIFY(XXH64_update(hashState, &m_defaultFramebufferHeight,
sizeof(m_defaultFramebufferHeight)));
}
// Include UBO block bindings in hash so different binding configurations produce different entries
const Uint32 blockCount = static_cast<Uint32>(program.GetActiveUniformBlocksCount());
XXHASH_VERIFY(XXH64_update(m_hashState, &blockCount, sizeof(blockCount)));
XXHASH_VERIFY(XXH64_update(hashState, &blockCount, sizeof(blockCount)));
for (Uint32 i = 0; i < blockCount; ++i) {
const Uint32 binding = program.GetUniformBlockBinding(i);
XXHASH_VERIFY(XXH64_update(m_hashState, &binding, sizeof(binding)));
XXHASH_VERIFY(XXH64_update(hashState, &binding, sizeof(binding)));
}
// The transform feedback capture layout is baked into the modules by
@@ -2605,18 +2607,18 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// hashed for a capturing compile, so nothing else changes key.
if (flags & CompileOptionBit::XfbCapture) {
for (const auto& varying : program.GetTransformFeedbackVaryings()) {
XXHASH_VERIFY(XXH64_update(m_hashState, varying.name.data(), varying.name.size()));
XXHASH_VERIFY(XXH64_update(m_hashState, &varying.bufferIndex, sizeof(varying.bufferIndex)));
XXHASH_VERIFY(XXH64_update(m_hashState, &varying.offsetBytes, sizeof(varying.offsetBytes)));
XXHASH_VERIFY(XXH64_update(hashState, varying.name.data(), varying.name.size()));
XXHASH_VERIFY(XXH64_update(hashState, &varying.bufferIndex, sizeof(varying.bufferIndex)));
XXHASH_VERIFY(XXH64_update(hashState, &varying.offsetBytes, sizeof(varying.offsetBytes)));
}
const SizeT bufferCount = program.GetTransformFeedbackBufferCount();
for (SizeT i = 0; i < bufferCount; ++i) {
const Uint32 stride = program.GetTransformFeedbackStride(static_cast<Uint32>(i));
XXHASH_VERIFY(XXH64_update(m_hashState, &stride, sizeof(stride)));
XXHASH_VERIFY(XXH64_update(hashState, &stride, sizeof(stride)));
}
}
HashType hash = XXH64_digest(m_hashState);
HashType hash = XXH64_digest(hashState);
return hash;
}