cuSPARSELt Data Types

Opaque Data Structures

cusparseLtHandle_t

The structure holds the cuSPARSELt library context (device properties, system information, etc.).

The handle must be initialized and destroyed with cusparseLtInit() and cusparseLtDestroy() functions respectively.

cusparseLtMatDescriptor_t

The structure captures the shape and characteristics of a matrix.

It is initialized with cusparseLtDenseDescriptorInit() or cusparseLtStructuredDescriptorInit() functions and destroyed with cusparseLtMatDescriptorDestroy().

cusparseLtMatmulDescriptor_t

The structure holds the description of the matrix multiplication operation.

It is initialized with cusparseLtMatmulDescriptorInit() function.

cusparseLtMatmulAlgSelection_t

The structure holds the description of the matrix multiplication algorithm.

It is initialized with cusparseLtMatmulAlgSelectionInit() function.

cusparseLtMatmulPlan_t

The structure holds the matrix multiplication execution plan, namely all the information necessary to execute the cusparseLtMatmul() operation.

It is initialized and destroyed with cusparseLtMatmulPlanInit() and cusparseLtMatmulPlanDestroy() functions respectively.

---

Enumerators

cusparseLtSparsity_t

The enumerator specifies the sparsity ratio of the structured matrix as

Value	Description
CUSPARSELT_SPARSITY_50_PERCENT	50% Sparsity Ratio: - 2:4 for half, bfloat16, int - 1:2 for tf32 and float

The sparsity property is used in the cusparseLtStructuredDescriptorInit() function.

---

cusparseComputeType

The enumerator specifies the compute precision modes of the matrix

Value	Description
CUSPARSE_COMPUTE_16F	- Default mode for 16-bit floating-point precision - All computations and intermediate storage ensure at least 16-bit precision - Tensor Cores will be used whenever possible
CUSPARSE_COMPUTE_32I	- Default mode for 32-bit integer precision - All computations and intermediate storage ensure at least 32-bit integer precision - Tensor Cores will be used whenever possible
CUSPARSE_COMPUTE_TF32_FAST	- Default mode for 32-bit floating-point precision - The inputs are supposed to be directly represented in TensorFloat-32 precision. The 32-bit floating-point values are truncated to TensorFloat-32 before the computation - All computations and intermediate storage ensure at least TensorFloat-32 precision - Tensor Cores will be used whenever possible
CUSPARSE_COMPUTE_TF32	- All computations and intermediate storage ensure at least TensorFloat-32 precision - The inputs are rounded to TensorFloat-32 precision. This mode is slower than CUSPARSE_COMPUTE_TF32_FAST, but could provide more accurate results - Tensor Cores will be used whenever possible

The compute precision is used in the cusparseLtMatmulDescriptorInit() function.

---

cusparseLtMatDescAttribute_t

The enumerator specifies the additional attributes of a matrix descriptor

Value	Description
CUSPARSELT_MAT_NUM_BATCHES	Number of matrices in a batch
CUSPARSELT_MAT_BATCH_STRIDE	Stride between consecutive matrices in a batch expressed in terms of matrix elements

The algorithm enumerator is used in the cusparseLtMatDescSetAttribute() and cusparseLtMatDescGetAttribute() functions.

---

cusparseLtMatmulDescAttribute_t

The enumerator specifies the additional attributes of a matrix multiplication descriptor

Value	Type	Default Value	Description
CUSPARSELT_MATMUL_ACTIVATION_RELU	int 0: false, true otherwise	false	ReLU activation function
CUSPARSELT_MATMUL_ACTIVATION_RELU_UPPERBOUND	float	inf	Upper bound of the ReLU activation function
CUSPARSELT_MATMUL_ACTIVATION_RELU_THRESHOLD	float	0.0f	Lower threshold of the ReLU activation function
CUSPARSELT_MATMUL_ACTIVATION_GELU	int 0: false, true otherwise	false	GeLU activation function
CUSPARSELT_MATMUL_BIAS_POINTER	void*	NULL (disabled)	Bias pointer. The bias vector size must equal to the number of rows of the output matrix (D)
CUSPARSELT_MATMUL_BIAS_STRIDE	int64_t	0 (disabled)	Bias stride between consecutive bias vectors. 0 means broadcast the first bias vector

where the ReLU activation function is defined as:

• The GeLU activation function is available only with INT8 input/output, INT32 Tensor Core compute kernels

The algorithm enumerator is used in the cusparseLtMatmulDescSetAttribute() and cusparseLtMatmulDescGetAttribute() functions.

---

cusparseLtMatmulAlg_t

The enumerator specifies the algorithm for matrix-matrix multiplication

Value	Description
CUSPARSELT_MATMUL_ALG_DEFAULT	Default algorithm

The algorithm enumerator is used in the cusparseLtMatmulAlgSelectionInit() function.

---

cusparseLtMatmulAlgAttribute_t

The enumerator specifies the matrix multiplication algorithm attributes

Value	Description
CUSPARSELT_MATMUL_ALG_CONFIG_ID	Algorithm ID (set and query)
CUSPARSELT_MATMUL_ALG_CONFIG_MAX_ID	Algorithm ID limit (query only)
CUSPARSELT_MATMUL_SEARCH_ITERATIONS	Number of iterations (kernel launches per algorithm) for cusparseLtMatmulSearch(), default=10

The algorithm attribute enumerator is used in the cusparseLtMatmulAlgGetAttribute() and cusparseLtMatmulAlgSetAttribute() functions.

---

cusparseLtPruneAlg_t

The enumerator specifies the pruning algorithm to apply to the structured matrix before the compression

Value	Description
CUSPARSELT_PRUNE_SPMMA_TILE	- half, bfloat16, int8: Zero-out eight values in a 4x4 tile to maximize the L1-norm of the resulting tile, under the constraint of selecting exactly two elements for each row and column   - float, tf32: Zero-out two values in a 2x2 tile to maximize the L1-norm of the resulting tile, under the constraint of selecting exactly one element for each row and column
CUSPARSELT_PRUNE_SPMMA_STRIP	- half, bfloat16, int8: Zero-out two values in a 1x4 strip to maximize the L1-norm of the resulting strip   - float, tf32: Zero-out one value in a 1x2 strip to maximize the L1-norm of the resulting strip   The strip direction is chosen according to the operation op and matrix layout applied to the structured (sparse) matrix

The pruning algorithm is used in the cusparseLtSpMMAPrune() function.