o ,ik@sddlZddlmZddlmZmZmZmZmZm Z ddl Z ddl m Z m Z ddlmZmZmZmZmZmZmZmZmZgdZeddZGd d d e jZ dd e jd edefddZGdddeZGdddeZdS)N) namedtuple)AnyOptionalTupleListCallableDict))sparse_semi_structured_from_dense_cutlass'sparse_semi_structured_to_dense_cutlass) fallback_dispatchersemi_sparse_valuessemi_sparse_indicessemi_sparse_detach semi_sparse_tsemi_sparse_viewsemi_sparse_mmsemi_sparse_addmmsemi_sparse_linear)SparseSemiStructuredTensor!SparseSemiStructuredTensorCUTLASS$SparseSemiStructuredTensorCUSPARSELTto_sparse_semi_structured_SEMI_STRUCTURED_SPARSE_CONFIGz=sparse_min_rows sparse_min_cols dense_min_rows dense_min_colsc@s"eZdZUdZdZeed<eej e fed<dZ e ed<dZ e ed<dZe ed <eed <eeefed <eejed <eejed <eejed<eejed<eejed<e ed<eed<gdZe   d4dejd eejd eejdeejdeejdeejde dede fddZdefddZdeeeeeje ee fffddZedeeje ee fdejfddZejjZede fd d!Z!ed5d6d#d$Z"ed%ejdd"fd&d'Z#ed(ejdejfd)d*Z$d+d,Z%ed%ejddfd-d.Z&d"d/d0ejd1eejdejfd2d3Z'd"S)7ra This class implementes semi-structured sparsity as a Tensor subclass. Semi-structured sparsity describes a sparsity pattern where n in every 2n elements are sparse, depending on the datatype. It is also referred to as 2:4 sparsity or fine-grained structured sparsity. There are two backends available for semi_structred sparsity, either cuSPARSELt or CUTLASS. This class is meant to serve as a base class for both implementations. SparseSemiStructuredCUTLASS and SparseSemiStructuredCUSPARSELT both inherit from this class and define three backend-specific items. Note that as such, this class cannot be insantiated directly. -`_DTYPE_SHAPE_CONSTRAINTS` - A dictionary holding backend specific dense/sparse min shape constraints - `def from_dense()` - backend specific compression routines - `def _mm()` - backend specifc mm op (either torch._cslt_sparse_mm or torch._sparse_semi_structured_(mm|addmm)) r_DEFAULT_ALG_ID_DTYPE_SHAPE_CONSTRAINTST_FORCE_CUTLASSF_FUSE_TRANSPOSE_PROTOTYPE_WARNING_SHOWNBACKENDSPARSE_DISPATCHpackedmetapacked_tmeta_tcompressed_swizzled_bitmaskfuse_transpose_cusparseltalg_id_cusparselt)r r!r"r#r$shape requires_gradc Cs|jstdtd|_|tj||dur|} n |dur$|} ntd| j | j | j | d} tj j ||fi| } || _|| _|| _|| _|| _|| _|| _| S)a0 Create a new instance of the tensor subclass from the compressed sparse representation. We have the option to create the subclass with the compressed representations of both X and X', for training. For inference, we only need a single representation (either X or X'), while the corresponding other set will be None. Depending on the backend selected, certain fields will be set to None. (CUSPARSELT vs CUTLASS) Args: shape: The shape of the original dense tensor packed: The compressed representation of the original dense tensor meta: The metadata of the original dense tensor, if it is stored separately packed_t: The compressed representation of the transposed original dense tensor meta_t: The metadata of the transposed original dense tensor, if it is stored separately compressed_swizzled_bitmask: The masks used by the CUTLASS backend to determine which threads should participate in the computation. Used for pointwise ops. fuse_transpose_cusparselt: When running with cuSPARSELt, we have the option to fuse a transposition with a matmul, which is useful in the case of 2:4 sparse training. alg_id_cusparselt: The algorithm id to use when using cuSPARSELT, will have effect on performance Returns: torch.Tensor: A torch.Tensor wrapper subclass. Raises: ValueError: If all of the tensor arguments are None. zThe PyTorch API of SparseSemiStructuredTensor is in prototype stage and will change in the near future. Please open a Github issue for features requests and see our documentation on the torch.sparse module for further information about the project.TNz3At least one of packed or packed_t must be provided)devicedtypelayoutr()rwarningswarn UserWarning_load_dispatch_tabletorch_dynamoallow_in_graph ValueErrorr)r*r+Tensor_make_wrapper_subclassr r!r"r#r$r%r&) clsr'r r!r"r#r$r%r&r(previous_tensorkwargstensorr:Z/home/ubuntu/SoloSpeech/.venv/lib/python3.10/site-packages/torch/sparse/semi_structured.py__new__Is6'  z"SparseSemiStructuredTensor.__new__returncCs$t|dsJ|jjd|jdS)Nr'z(shape=))hasattr __class____name__r'selfr:r:r;__repr__sz#SparseSemiStructuredTensor.__repr__cs4ttfddj}jjjjf}||fS)Ncst|duSN)getattr)xrBr:r;sz?SparseSemiStructuredTensor.__tensor_flatten__..)listfilter __slots__r'r%r&r()rC inner_tensors tensor_metar:rBr;__tensor_flatten__sz-SparseSemiStructuredTensor.__tensor_flatten__rMc CsN|\}}}}|||dd|dd|dd|dd|dd|||d S)Nr r!r"r#r$ r'r r!r"r#r$r%r&r()get) r6rLrM outer_size outer_strider'r%r&r(r:r:r;__tensor_unflatten__s      z/SparseSemiStructuredTensor.__tensor_unflatten__cCs:|j|jvrt|jd|jd|j|j||||S)NzI only supports a specific set of operations, can't perform requested op (r>)_overloadpacketrNotImplementedErrorrA)r6functypesargsr8r:r:r;__torch_dispatch__s z-SparseSemiStructuredTensor.__torch_dispatch__NcCst|dddurStjjjttjjjttjjjt tjjj t tjjj t tjjj ttjjjttjjjttjjjttjjjttjjjttjjjt i |_|durU|j|dSdSdS)zT Loads the op overload sparse dispatch table for the current class. rN)rFr0opsatenvaluesr indicesr is_same_sizer detach_detachrtrviewrmmrmatmuladdmmrlinearr_to_copyrupdate)r6custom_dispatch_tabler:r:r;r/s$            z/SparseSemiStructuredTensor._load_dispatch_tableoriginal_tensorcCs|js td|jd|dkrtd|d|s$td|j|jvr3td|jd|j\}}|j|jj}|j|jj }||ksV||sV||ksV||retd |jd |d |d d S)z_ Assert that the given tensor is valid for semi-structured sparse compression. zError original_tensor.device= z= is not supported! Only CUDA tensors are currently supported.zError original_tensor.dim = z; is not supported! Only 2d tensors are currently supported.zXError original_tensor is not contiguous!Only contiguous tensors are currently supported.zError original_tensor.dtype zO is not a supported dtype! dtype must be one of: {cls._DTYPE_SHAPE_CONSTRAINTS}zError original_tensor.shape zS is not supported! Both dimensions must be larger or equal than and a multiple of (z, r>N) is_cuda RuntimeErrorr)dim is_contiguousr*rr'sparse_min_rowssparse_min_cols)r6rjmnmin_rowsmin_colsr:r:r; _validate_device_dim_dtype_shapes8       z;SparseSemiStructuredTensor._validate_device_dim_dtype_shape dense_inputcCs|dksJ|j\}}|j|jj}|j|jj}||ks#||r(| |nd}||ks2||r7| |nd}|s=|rItjj |d|d|fS|S)z Calculates padding for dense tensor and pads tensor if necessary. If padding is not required, this function returns the original tensor. rkr) rnr'rr*dense_min_rowsdense_min_colsr0nn functionalpad)r6rwrrrsrtruto_pad_mto_pad_nr:r:r;_pad_dense_inputs z+SparseSemiStructuredTensor._pad_dense_inputcCs&|jd}t|tj||j|jdS)N)r*r))r'r0rceyer*r))rCcolr:r:r;to_dense's z#SparseSemiStructuredTensor.to_densecCtrErUr6rjr:r:r; from_dense+sz%SparseSemiStructuredTensor.from_densebiasBrcKrrEr)rCrrr8r:r:r;_mm/szSparseSemiStructuredTensor._mm)FrFrE)r=N)(rA __module__ __qualname____doc__rint__annotations__rr0r*rrboolrrstrrrr4rK staticmethodSizer<rDrrrN classmethodrS_C_disabled_torch_function_impl__torch_function__rrYr/rvrrrrr:r:r:r;r$s        R  +rFrj transposedr=cCs4|r tjdtddtjrtjjntjj}| |S)a This function converts a dense tensor into a sparse semi-structured tensor. It will return a SparseSemiStructuredTensor, a subclass of torch.Tensor. This function will check to ensure the dense tensor has the right dtype, size, dims, and device. We currently only support semi-structured sparse tensors for 2d CUDA tensors. Additionally, your tensor must be a positive multiple of the mininum sparse block size, given in `_DTYPE_TO_SHAPE_CONSTRAINTS` for each dtype (float32, float16, bfloat16, int8). Args: original_tensor (Tensor): the dense tensor to convert transposed (bool, optional): deprecated arg to be removed in another release. Do not use. Returns: SparseSemiStructuredTensor: A sparse semi-structured tensor created from the given original_tensor Raises: None Example: >>> # xdoctest: +REQUIRES(env:TORCH_DOCTEST_CUDA) >>> A = torch.Tensor([0, 0, 1, 1]).tile((128, 32)).half().cuda() tensor([[0., 0., 1., ..., 0., 1., 1.], [0., 0., 1., ..., 0., 1., 1.], [0., 0., 1., ..., 0., 1., 1.], ..., [0., 0., 1., ..., 0., 1., 1.], [0., 0., 1., ..., 0., 1., 1.], [0., 0., 1., ..., 0., 1., 1.]], device='cuda:0', dtype=torch.float16) >>> A_sparse = to_sparse_semi_structured(A) SparseSemiStructuredTensor(shape=torch.Size([128, 128])) >>> A_sparse.values() tensor([[1., 1., 1., ..., 1., 1., 1.], [1., 1., 1., ..., 1., 1., 1.], [1., 1., 1., ..., 1., 1., 1.], ..., [1., 1., 1., ..., 1., 1., 1.], [1., 1., 1., ..., 1., 1., 1.], [1., 1., 1., ..., 1., 1., 1.]], device='cuda:0', dtype=torch.float16), >>> A_sparse.indices() tensor([[-4370, -4370, -4370, ..., -4370, -4370, -4370], [-4370, -4370, -4370, ..., -4370, -4370, -4370], [-4370, -4370, -4370, ..., -4370, -4370, -4370], ..., [-4370, -4370, -4370, ..., -4370, -4370, -4370], [-4370, -4370, -4370, ..., -4370, -4370, -4370], [-4370, -4370, -4370, ..., -4370, -4370, -4370]], device='cuda:0', dtype=torch.int16)) zSetting transpose from `to_sparse_semi_structured` is deprecated and will be removed in a future release. `SparseSemiStructuredTensor` only support contiguous input tensors.rk) stacklevel) r,r- FutureWarningrrr0sparserrr)rjrSPARSE_SUBCLASSr:r:r;r9s1  rc seZdZdZdZejeddddejeddddej eddddej eddddiZ e d ej d dfd d Zfd dZe dd ej d dfddZdddej deej d ej fddZZS)ra This class implements semi-structured sparsity for the CUTLASS backend. In this implementation, the specified elements and metadata are stored seprately, in packed and meta respectively. When _FORCE_CUTLASS is set, or when cuSPARSELt is not available, this subclass calls into _sparse_semi_structured_(mm|addmm) and sparse_semi_structured_from_dense for conversion to the compressed format. cutlass @rjr=c Cs0||t|\}}||j||ddd|jdS)Nr r!r"r#r$r()rvr r'r()r6rjsparse_tensor_cutlassmeta_tensor_cutlassr:r:r;rs z,SparseSemiStructuredTensorCUTLASS.from_densecs<|jdur |jdus J|jjdkrt|j|jStS)Nrk)r!r ndimr superrrBr@r:r;rs z*SparseSemiStructuredTensorCUTLASS.to_denserc Cs2tj||dd\}}}}}||j|||||ddS)a This function takes in a unpruned dense tensor and runs a (branchless) static sort across a 4x4 tile. It greedily picks the largest values in the tile, upholding the 2:4 sparsity constraint across both rows and columns. The algorithm used to prune the matrix is implemented in `_sparse_semi_structured_tile`. Then it creates the packed and meta tensors for the compressed sparse representation of the pruned dense tensor. It also calculates the packed_t and meta_t tensors for the compressed sparse representation of the transposed pruned dense tensor. Since we cannot transpose the compressed representations, we store both for the fw/bw pass respectively. Finally, this function also computes a compressed swizzled bitmask that encodes the sparsity pattern This can be used in the backward pass to mask the gradients. [9 1 7 4] [9 0 7 0] [1 2 3 0] [0 2 0 0] [8 3 5 4] -> prune 4x4 tile -> [8 0 0 4] -> pack to CUTLASS semi-structured -> packed [1 2 6 2] [0 0 6 2] -> metadata -> pack to transposed CUTLASS -> packed_t semi-structured representation -> metadata_t -> compute swizzled bitmask -> compressed_swizzled_bitmask The equivalent PyTorch code to create the same five outputs from the dense tensor can be found below: ``` from torch.sparse import SparseSemiStructuredTensorCUTLASS from torch.sparse._semi_structured_conversions import _sparse_semi_structured_tile, _compute_compressed_swizzled_bitmask pruned = _sparse_semi_structured_tile(dense) packed_cutlass, meta_cutlass = sparse_semi_structured_from_dense_cutlass(pruned) packed_t_cutlass, meta_t_cutlass = sparse_semi_structured_from_dense_cutlass(pruned.t().contiguous()) bitmask = _compute_compressed_swizzled_bitmask(pruned) SparseSemiStructuredTensorCUTLASS(dense.shape, packed_cutlass, meta_cutlass, packed_t_cutlass, meta_t_cutlass, bitmask) ``` T algorithm use_cutlassFrr0_sparse_semi_structured_tiler'r6rjrr r!r"r#r$r:r:r;prune_dense_static_sorts)z9SparseSemiStructuredTensorCUTLASS.prune_dense_static_sortNrrrcKst|tr td|jj}|jdks|jdkrtd|d|jdus)|jdur1td|d|dur?t |j|j|}n t ||j|j|}|d|j dS)NZ`SparseSemiStructuredTensor @ SparseSemiStructuredTensor` is not supported by the hardwarerk`)` matmul: Broadcasting is not implemented$` matmul: operation is not supportedr) isinstancerr3r@rArrUr r!r0_sparse_semi_structured_mm_sparse_semi_structured_addmmr')rCrrr8cls_nameresr:r:r;rs*     z%SparseSemiStructuredTensorCUTLASS._mmr)rArrrrr0int8rfloat16bfloat16float32rrr4rrrrr __classcell__r:r:rr;r|s2  ;rc @seZdZdZdZejeddddejeddddej eddddej eddddiZ e dej ddfd d Ze ddej dd fd dZdddej deej dej fddZdS)ra The cuSPARSELt backend expects the specified elements and the metadata to be stored in a single tensor: packed = [ specified elements of original tensor | metadata ] For an original tensor of size (m, k) we expect the first m * k // 2 elements to be the kept elements The rest of the tensor is metadata. Since there is only one tensor, we only use the packed and packed_t attributes respectively. cuSPARSELt also supports transposition fusion, which is necessary for performant 2:4 sparse training, as well as specifying alg_id, a config that affects the performance of the matmul depending on matmul sizes. cusparseltrrrrrjr=c Cs2||||jt|ddddtjtj|jd S)NrO)rvr'r0_cslt_compressrrrr(rr:r:r;rs z/SparseSemiStructuredTensorCUSPARSELT.from_denserrc Cs2tj||dd\}}}}}||j|||||ddS)a This function does the same thing as described in SparseSemiStructuredCUTLASS, but uses the cuSPASRELt metadata layout and sparse matmul. The only functional difference is that cuSPARSELt stores `metadata` and `packed` together into a single tensor. [9 1 7 4] [9 0 7 0] [1 2 3 0] [0 2 0 0] [8 3 5 4] -> prune 4x4 tile -> [8 0 0 4] -> pack to cuSPARSELT semi-structured -> packed [1 2 6 2] [0 0 6 2] -> pack to transposed cuSPARSELt -> packed_t semi-structured representation -> compute swizzled bitmask -> compressed_swizzled_bitmask The equivalent PyTorch code to create the same three outputs from the dense tensor can be found below: ``` from torch.sparse import SparseSemiStructuredTensorCUSPARSELT from torch.sparse._semi_structured_conversions import _sparse_semi_structured_tile, _compute_compressed_swizzled_bitmask pruned = _sparse_semi_structured_tile(dense) packed_cusparselt = torch._cslt_compress(pruned) packed_t_cusparselt = torch._cslt_compress(pruned.t().contiguous()) bitmask = _compute_compressed_swizzled_bitmask(pruned) SparseSemiStructuredTensorCUSPARSELT(dense.shape, packed_cutlass, None, packed_t_cutlass, None, bitmask) ``` Frrrrr:r:r;r#s zs2  ,  C