MayaFlux 1.0.0
Digital-First Multimedia Processing Framework
Loading...
Searching...
No Matches
Stages.hpp File Reference

The stages that run the tensor kernels. More...

Include dependency graph for Stages.hpp:
This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Namespaces

namespace  MayaFlux
 Main namespace for the Maya Flux audio engine.
namespace  MayaFlux::Yantra
namespace  MayaFlux::Yantra::TensorKernels
namespace  MayaFlux::Yantra::TensorKernels::detail

Functions

DependencyStage MayaFlux::Yantra::TensorKernels::add_stage (uint64_t a, uint64_t b, uint64_t dst, uint32_t count)
 One nn_add dispatch: the element-wise sum of two sequences of count floats.
DependencyStage MayaFlux::Yantra::TensorKernels::attention_mix_stage (uint64_t weights, uint64_t v, uint64_t dst, uint32_t heads, uint32_t dim, uint32_t time)
 One nn_attention_mix dispatch: the values of every position mixed by each query's attention weights.
DependencyStage MayaFlux::Yantra::TensorKernels::attention_scores_stage (uint64_t q, uint64_t k, uint64_t scores, uint32_t heads, uint32_t dim, uint32_t time, float scale)
 One nn_attention_scores dispatch: scale times the dot product of every query with every key, per head.
DependencyStage MayaFlux::Yantra::TensorKernels::conv1d_stage (const Conv1d &layer, uint64_t src, uint64_t weights, uint64_t bias, uint64_t dst, uint32_t batch, uint32_t t_in)
 One nn_conv1d dispatch: [batch, c_in, t_in] to [batch, c_out, conv1d_length].
DependencyStage MayaFlux::Yantra::TensorKernels::frame_audio_stage (uint64_t samples, uint64_t frames, uint32_t chunks, uint32_t chunk_size, uint32_t context, uint32_t pad)
 One nn_frame_audio dispatch: cut a sample stream into overlapping frames, reflect padded on the right.
std::array< uint32_t, 3 > MayaFlux::Yantra::TensorKernels::detail::group_grid (size_t invocations, uint32_t local)
 Workgroup counts covering the invocations, along x up to max_groups_per_axis and then along y.
DependencyStage MayaFlux::Yantra::TensorKernels::grouped_conv1d_stage (const GroupedConv1d &layer, uint64_t src, uint64_t weights, uint64_t bias, uint64_t dst, uint32_t batch, uint32_t t_in)
 One nn_conv1d_grouped dispatch: [batch, c_in, t_in] to [batch, c_out, grouped_conv1d_length].
uint32_t MayaFlux::Yantra::TensorKernels::detail::groups_for (size_t invocations, uint32_t local)
DependencyStage MayaFlux::Yantra::TensorKernels::lstm_sequence_stage (uint64_t x, uint64_t w_ih, uint64_t w_hh, uint64_t b_ih, uint64_t b_hh, uint64_t state, uint64_t hs, uint32_t steps, uint32_t hidden)
 One nn_lstm_sequence dispatch: an LSTM cell over a whole sequence in one workgroup.
DependencyStage MayaFlux::Yantra::TensorKernels::magnitude_stage (uint64_t src, uint64_t dst, uint32_t batch, uint32_t channels, uint32_t time)
 One nn_magnitude dispatch: sqrt(re^2 + im^2) of a complex signal stored as two channel halves.
template<typename PC>
DependencyStage MayaFlux::Yantra::TensorKernels::detail::make_grid_stage (const char *shader, const PC &pc, size_t invocations)
template<typename PC>
DependencyStage MayaFlux::Yantra::TensorKernels::detail::make_stage (const char *shader, uint32_t local, const PC &pc, uint32_t groups)
DependencyStage MayaFlux::Yantra::TensorKernels::normalize_apply_stage (uint64_t src, uint64_t stats, uint64_t weight, uint64_t bias, uint64_t dst, uint32_t outer, uint32_t extent, uint32_t inner, NormAffine affine, Activation activation=Activation::None)
 The nn_normalize dispatch that writes (x - mean) * scale from the measures of normalize_stats_stage.
DependencyStage MayaFlux::Yantra::TensorKernels::normalize_stats_stage (uint64_t src, uint64_t stats, uint32_t outer, uint32_t extent, uint32_t inner, float epsilon)
 The nn_normalize dispatch that measures every row of a tensor [outer, extent, inner] along extent.
DependencyStage MayaFlux::Yantra::TensorKernels::softmax_stage (uint64_t data, uint32_t outer, uint32_t extent, uint32_t inner)
 One nn_softmax dispatch: softmax of a tensor [outer, extent, inner] along extent, in place.

Detailed Description

The stages that run the tensor kernels.

Each function returns a DependencyStage for record_stages, so a network is a list of stages recorded into one submission. Addresses are device addresses of float32 buffers, from a context's shared buffers (shared_buffer_address).

Definition in file Stages.hpp.