cuBALS使用（5）-cublasXt

创始人

2025-05-30 01:18:33

cuBLAS的cuBLASXt API提供支持多GPU的主机接口：当使用该API时，应用程序仅需要在主机存储器空间上分配所需的矩阵。矩阵的大小没有限制，只要它们可以放入主机存储器即可。cuBLASXt API负责在指定的GPU之间分配内存，并在它们之间分派工作负载，最后将结果检索回主机。cuBLASXt API仅支持计算密集型BLAS 3例程（例如矩阵-矩阵运算），在这些例程中，来自GPU的PCI来回传输可以分摊。cuBLASXt API有自己的头文件cublasXt.h。
从8.0版开始，cuBLASXt API允许将任何矩阵放置在GPU设备上。
注意：cuBLASXt API仅在64位平台上受支持。

平铺设计方法

为了能够在多个GPU之间分担工作负载，cuBLASXt API使用了一种平铺策略：每个矩阵被分成用户可控尺寸BlockDim × BlockDim的正方形块。生成的矩阵平铺定义静态调度策略：每一所得瓦片以循环方式作用于GPU。每一GPU创建一个CPU线程，且所述CPU线程负责进行适当的存储器传送和CUBLAS操作以计算其所负责的所有瓦片。从性能的角度来看，由于这种静态调度策略，最好每个GPU的计算能力和PCI带宽都相同。下图说明了3个GPU之间的图块分布。为了从C计算第一瓦片G0，负责GPU0的CPU线程0必须以管线方式加载来自A的第一行的3个瓦片和来自B的第一列的瓦片，以便重叠存储器传送和计算，且在移动到下一瓦片G0之前将结果求和到C的第一瓦片G0中。

当块尺寸不是C的尺寸的精确倍数时，一些块在右边界或/和底部边界上被部分填充。当前的实现不会填充不完整的图块，而是通过执行正确的简化cuBLAS操作来跟踪这些不完整的图块：这样就不会进行额外的计算。然而，当所有GPU没有相同数量的不完整瓦片工作时，它仍然可以导致一些负载不平衡。
当一个或多个矩阵位于某些GPU设备上时，应用相同的平铺方法和工作负载共享。在这种情况下，存储器传输在设备之间进行。然而，当图块的计算和一些数据位于同一GPU设备上时，绕过将本地数据传输到图块或从本地数据传输到图块的存储器传输，并且GPU直接对本地数据进行操作。这可以显著提高性能，尤其是在仅使用一个GPU进行计算时。
矩阵可以位于任何GPU设备上，并且不必位于同一GPU设备上。此外，矩阵甚至可以位于不参与计算的GPU设备上。
与cuBLAS API相反，即使所有矩阵都位于同一设备上，从主机的角度来看，cuBLASXt API仍然是一个阻塞API：无论位于何处的数据结果在呼叫返回时都将是有效的，并且不需要设备同步。

Hybrid CPU-GPU computation

在出现非常大的问题时，cuBLASXt API可以将部分计算卸载到主机CPU。此功能可通过cublasXtSetCpuRoutine（）和cublasXtSetCpuRatio（）例程设置。影响CPU的工作负载被搁置：它仅仅是从底部和右侧取的所得矩阵的百分比，无论哪个维度较大。GPU平铺是在这之后在减少的结果矩阵上完成的。
如果任何矩阵位于GPU设备上，则将忽略该功能，并且所有计算都将仅在GPU上完成
应谨慎使用此功能，因为它可能会干扰负责为GPU提供数据的CPU线程。
目前，只有cublasXtgemm（）例程支持此特性。

Results reproducibility

当前，给定工具包版本中的所有CUBLAS XT API例程在满足以下条件时生成相同的按位结果：

参与计算的所有GPU具有相同的计算能力和相同数量的SM。
在运行之间块尺寸保持相同。
或者不使用CPU混合计算，或者也保证所提供的CPUBlas产生可再现的结果。

cuBLASXt API数据类型

cublasXtHandle_ t

该 cublasXtHandle_t是指向保存cuBLASXt API上下文的不透明结构的指针类型。必须使用以下命令初始化cublasXtHandle_t 并且返回的句柄必须传递给所有后续的cuBLASXt API函数调用。上下文应在最后使用cublasXtDestroy() 。

cublasXtOpType_t

该cublasOptype_t枚举了四种可能得类型，此枚举用作里程的参数cublasXtSetCpuRotine和cublasXtSetCpuRation建立对应额混合的配置。

Value	Meaning
`CUBLASXT_FLOAT`	浮点或单精度类型
`CUBLASXT_DOUBLE`	双精度类型
`CUBLASXT_COMPLEX`	单精度复数
`CUBLASXT_DOUBLECOMPLEX`	双精度复数

cublasXtBlasOp_t

该 cublasXtBlasOp_t 类型列举了由cuBLASXt API支持的BLAS3或类BLAS3程序。此枚举用作例程的参数cublasXtSetCpuRoutine 以及 cublasXtSetCpuRoutine 以建立混合配

cublasXtSetCpuRoutine

Value	Meaning
`CUBLASXT_GEMM`	GEMM routine
`CUBLASXT_SYRK`	SYRK routine
`CUBLASXT_HERK`	HERK routine
`CUBLASXT_SYMM`	SYMM routine
`CUBLASXT_HEMM`	HEMM routine
`CUBLASXT_TRSM`	TRSM routine
`CUBLASXT_SYR2K`	SYR2K routine
`CUBLASXT_HER2K`	HER2K routine
`CUBLASXT_SPMM`	SPMM routine
`CUBLASXT_SYRKX`	SYRKX routine
`CUBLASXT_HERKX`	HERKX routine

cublasXtPinningMemMode_t

该类型用于通过例程启用或禁用固定存储器模式cubasMgSetPinningMemMode

Value	Meaning
`CUBLASXT_PINNING_DISABLED`	the Pinning Memory mode is disabled
`CUBLASXT_PINNING_ENABLED`	the Pinning Memory mode is enabled

cuBLASXt API Helper Function Reference

cublasXtCreate()

cublasStatus_t
cublasXtCreate(cublasXtHandle_t *handle)

此函数用于初始化cuBLASXt API，并为保存cuBLASXt API上下文的不透明结构创建句柄。它分配主机和设备上的硬件资源，必须在进行任何其他cuBLASXt API调用之前调用。

Return Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the initialization succeeded
`CUBLAS_STATUS_ALLOC_FAILED`	the resources could not be allocated
`CUBLAS_STATUS_NOT_SUPPORTED`	cuBLASXt API is only supported on 64-bit platform

cublasXtDestroy()

cublasStatus_t
cublasXtDestroy(cublasXtHandle_t handle)

此函数用于释放cuBLASXt API上下文使用的硬件资源。GPU资源的释放可以被延迟直到应用退出。此函数通常是对cuBLASXt API的最后一次调用，具有特定句柄。

Return Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the shut down succeeded
`CUBLAS_STATUS_NOT_INITIALIZED`	the library was not initialized

cublasXtDeviceSelect()

cublasXtDeviceSelect(cublasXtHandle_t handle, int nbDevices, int deviceId[])

此函数允许用户提供将参与后续cuBLASXt API数学函数调用的GPU设备数量及其各自的ID。此函数将为列表中提供的每个GPU创建一个cuBLAS上下文。当前设备配置是静态的，不能在Math函数调用之间更改。在这方面，此函数应仅在cublasXtCreate之后调用一次。为了能够运行多个配置，应创建多个cuBLASXt API上下文。

Return Value	Meaning
`CUBLAS_STATUS_SUCCESS`	User call was sucessful
`CUBLAS_STATUS_INVALID_VALUE`	Access to at least one of the device could not be done or a cuBLAS context could not be created on at least one of the device
`CUBLAS_STATUS_ALLOC_FAILED`	Some resources could not be allocated.

cublasXtSetBlockDim()

cublasXtSetBlockDim(cublasXtHandle_t handle, int blockDim)

此函数允许用户设置用于后续Math函数调用的矩阵平铺的块维数。矩阵拆分为blockDim x blockDim维度的正方形块。此函数可随时调用，并将对以下Math函数调用生效。块尺寸的选择应优化数学运算，并确保PCI传输与计算良好重叠。

Return Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the call has been successful
`CUBLAS_STATUS_INVALID_VALUE`	blockDim <= 0

cublasXtGetBlockDim()

cublasXtGetBlockDim(cublasXtHandle_t handle, int *blockDim)

此函数允许用户查询用于矩阵平铺的块尺寸。

Return Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the call has been successful

cublasXtSetCpuRoutine()

cublasXtSetCpuRoutine(cublasXtHandle_t handle, cublasXtBlasOp_t blasOp, cublasXtOpType_t type, void *blasFunctor)

此函数允许用户提供相应BLAS例程的CPU实现。此函数可与cublasXtSetCpuRatio（）函数一起使用，以定义CPU和GPU之间的混合计算。目前，仅xGEMM例程支持混合功能。

Return Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the call has been successful
`CUBLAS_STATUS_INVALID_VALUE`	blasOp or type define an invalid combination
`CUBLAS_STATUS_NOT_SUPPORTED`	CPU-GPU Hybridization for that routine is not supported

cublasXtSetCpuRatio()

cublasXtSetCpuRatio(cublasXtHandle_t handle, cublasXtBlasOp_t blasOp, cublasXtOpType_t type, float ratio )

此函数允许用户定义在混合计算环境中应在CPU上完成的工作负载百分比。此函数可与cublasXtSetCpuRoutine（）函数一起使用，以定义CPU和GPU之间的混合计算。目前，仅xGEMM例程支持混合功能。

Return Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the call has been successful
`CUBLAS_STATUS_INVALID_VALUE`	blasOp or type define an invalid combination
`CUBLAS_STATUS_NOT_SUPPORTED`	CPU-GPU Hybridization for that routine is not supported

cublasXtSetPinningMemMode()

cublasXtSetPinningMemMode(cublasXtHandle_t handle, cublasXtPinningMemMode_t mode)

此功能允许用户启用或禁用固定的储器模式。启用后，如果矩阵尚未固定，则将分别使用CUDART例程cudaHostRegister和cudaHostUnregister固定/取消固定后续cuBLASXt API调用中传递的矩阵。如果矩阵碰巧被部分固定，则它也不会被固定。固定内存可提高PCI传输性能，并允许PCI内存传输与计算重叠。然而，固定/取消固定内存需要一些时间，这可能不会摊销。建议用户使用cudaMallocHost或cudaHostRegister自行固定存储器，并在计算序列完成时将其解锁。默认情况下，“固定内存”模式处于禁用状态。

当用于不同cuBLASXt API调用的矩阵重叠时，不应启用固定内存模式。如果使用cudaHostGetFlags固定了矩阵的第一个地址，则cuBLASXt确定该矩阵是否固定，因此无法知道该矩阵是否已经部分固定。这在多线程应用程序中尤其如此，在多线程应用程序中，当另一个线程正在访问内存时，内存可能会部分或全部被固定或取消固定。

Return Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the call has been successful
`CUBLAS_STATUS_INVALID_VALUE`	the mode value is different from `CUBLASXT_PINNING_DISABLED` and `CUBLASXT_PINNING_ENABLED`

cublasXtGetPinningMemMode()

cublasXtGetPinningMemMode(cublasXtHandle_t handle,cublasXtPinningMemMode_t *mode)

此功能允许用户查询引固定储器模式。默认情况下，“固定内存”模式处于禁用状态。

Return Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the call has been successful

cuBLASXt API Math Functions Reference

在本章中，我们将介绍cuBLASXt API支持的实际Linear Agebra例程。我们将使用type和相应的短类型的缩写，以便更简洁和清楚地表示所实现的函数。除非另有说明，具有下列含义：

		Meaning
`float`	‘s’ or ‘S’	real single-precision
`double`	‘d’ or ‘D’	real double-precision
`cuComplex`	‘c’ or ‘C’	complex single-precision
`cuDoubleComplex`	‘z’ or ‘Z’	complex double-precision

cublasXtgemm()

cublasStatus_t cublasXtSgemm(cublasXtHandle_t handle,cublasOperation_t transa, cublasOperation_t transb,size_t m, size_t n, size_t k,const float           *alpha,const float           *A, int lda,const float           *B, int ldb,const float           *beta,float           *C, int ldc)
cublasStatus_t cublasXtDgemm(cublasXtHandle_t handle,cublasOperation_t transa, cublasOperation_t transb,int m, int n, int k,const double          *alpha,const double          *A, int lda,const double          *B, int ldb,const double          *beta,double          *C, int ldc)
cublasStatus_t cublasXtCgemm(cublasXtHandle_t handle,cublasOperation_t transa, cublasOperation_t transb,int m, int n, int k,const cuComplex       *alpha,const cuComplex       *A, int lda,const cuComplex       *B, int ldb,const cuComplex       *beta,cuComplex       *C, int ldc)
cublasStatus_t cublasXtZgemm(cublasXtHandle_t handle,cublasOperation_t transa, cublasOperation_t transb,int m, int n, int k,const cuDoubleComplex *alpha,const cuDoubleComplex *A, int lda,const cuDoubleComplex *B, int ldb,const cuDoubleComplex *beta,cuDoubleComplex *C, int ldc)

此函数执行矩阵-矩阵乘法

Param.	Memory	In/out	Meaning
handle		input	handle to the cuBLASXt API context.
transa		input	operation op(`A`) that is non- or (conj.) transpose.
transb		input	operation op(`B`) that is non- or (conj.) transpose.
m		input	number of rows of matrix op(`A`) and `C`.
n		input	number of columns of matrix op(`B`) and `C`.
k		input	number of columns of op(`A`) and rows of op(`B`).
alpha	host	input	scalar used for multiplication.
A	host or device	input	array of dimensions `lda x k` with `lda>=max(1,m)` if `transa == CUBLAS_OP_N` and `lda x m` with `lda>=max(1,k)` otherwise.
lda		input	leading dimension of two-dimensional array used to store the matrix `A`.
B	host or device	input	array of dimension `ldb x n` with `ldb>=max(1,k)` if `transb == CUBLAS_OP_N` and `ldb x k` with `ldb>=max(1,n)` otherwise.
ldb		input	leading dimension of two-dimensional array used to store matrix `B`.
beta	host	input	scalar used for multiplication. If `beta==0`, `C` does not have to be a valid input.
C	host or device	in/out	array of dimensions `ldc x n` with `ldc>=max(1,m)`.
ldc		input	leading dimension of a two-dimensional array used to store the matrix `C`.

The possible error values returned by this function and their meanings are listed below.

Error Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the operation completed successfully
`CUBLAS_STATUS_NOT_INITIALIZED`	the library was not initialized
`CUBLAS_STATUS_INVALID_VALUE`	the parameters `m,n,k<0`
`CUBLAS_STATUS_EXECUTION_FAILED`	the function failed to launch on the GPU

cublasXthemm()

cublasStatus_t cublasXtChemm(cublasXtHandle_t handle,cublasSideMode_t side, cublasFillMode_t uplo,size_t m, size_t n,const cuComplex       *alpha,const cuComplex       *A, size_t lda,const cuComplex       *B, size_t ldb,const cuComplex       *beta,cuComplex       *C, size_t ldc)
cublasStatus_t cublasXtZhemm(cublasXtHandle_t handle,cublasSideMode_t side, cublasFillMode_t uplo,size_t m, size_t n,const cuDoubleComplex *alpha,const cuDoubleComplex *A, size_t lda,const cuDoubleComplex *B, size_t ldb,const cuDoubleComplex *beta,cuDoubleComplex *C, size_t ldc)

此函数执行厄米特矩阵-矩阵乘法

Param.	Memory	In/out	Meaning
handle		input	handle to the cuBLASXt API context.
side		input	indicates if matrix `A` is on the left or right of `B`.
uplo		input	indicates if matrix `A` lower or upper part is stored, the other Hermitian part is not referenced and is inferred from the stored elements.
m		input	number of rows of matrix `C` and `B`, with matrix `A` sized accordingly.
n		input	number of columns of matrix `C` and `B`, with matrix `A` sized accordingly.
alpha	host	input	scalar used for multiplication.
A	host or device	input	array of dimension `lda x m` with `lda>=max(1,m)` if `side==CUBLAS_SIDE_LEFT` and `lda x n` with `lda>=max(1,n)` otherwise. The imaginary parts of the diagonal elements are assumed to be zero.
lda		input	leading dimension of two-dimensional array used to store matrix `A`.
B	host or device	input	array of dimension `ldb x n` with `ldb>=max(1,m)`.
ldb		input	leading dimension of two-dimensional array used to store matrix `B`.
beta	host	input	scalar used for multiplication, if `beta==0` then `C` does not have to be a valid input.
C	host or device	in/out	array of dimensions `ldc x n` with `ldc>=max(1,m)`.
ldc		input	leading dimension of two-dimensional array used to store matrix `C`.

The possible error values returned by this function and their meanings are listed below.

Error Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the operation completed successfully
`CUBLAS_STATUS_NOT_INITIALIZED`	the library was not initialized
`CUBLAS_STATUS_INVALID_VALUE`	the parameters `m,n<0`
`CUBLAS_STATUS_EXECUTION_FAILED`	the function failed to launch on the GPU

cublasXtsymm()

cublasStatus_t cublasXtSsymm(cublasXtHandle_t handle,cublasSideMode_t side, cublasFillMode_t uplo,size_t m, size_t n,const float           *alpha,const float           *A, size_t lda,const float           *B, size_t ldb,const float           *beta,float           *C, size_t ldc)
cublasStatus_t cublasXtDsymm(cublasXtHandle_t handle,cublasSideMode_t side, cublasFillMode_t uplo,size_t m, size_t n,const double          *alpha,const double          *A, size_t lda,const double          *B, size_t ldb,const double          *beta,double          *C, size_t ldc)
cublasStatus_t cublasXtCsymm(cublasXtHandle_t handle,cublasSideMode_t side, cublasFillMode_t uplo,size_t m, size_t n,const cuComplex       *alpha,const cuComplex       *A, size_t lda,const cuComplex       *B, size_t ldb,const cuComplex       *beta,cuComplex       *C, size_t ldc)
cublasStatus_t cublasXtZsymm(cublasXtHandle_t handle,cublasSideMode_t side, cublasFillMode_t uplo,size_t m, size_t n,const cuDoubleComplex *alpha,const cuDoubleComplex *A, size_t lda,const cuDoubleComplex *B, size_t ldb,const cuDoubleComplex *beta,cuDoubleComplex *C, size_t ldc)

此函数执行对称矩阵-矩阵乘法

Param.	Memory	In/out	Meaning
handle		input	handle to the cuBLASXt API context.
side		input	indicates if matrix `A` is on the left or right of `B`.
uplo		input	indicates if matrix `A` lower or upper part is stored, the other symmetric part is not referenced and is inferred from the stored elements.
m		input	number of rows of matrix `A` and `B`, with matrix `A` sized accordingly.
n		input	number of columns of matrix `C` and `A`, with matrix `A` sized accordingly.
alpha	host	input	scalar used for multiplication.
A	host or device	input	array of dimension `lda x m` with `lda>=max(1,m)` if `side == CUBLAS_SIDE_LEFT` and `lda x n` with `lda>=max(1,n)` otherwise.
lda		input	leading dimension of two-dimensional array used to store matrix `A`.
B	host or device	input	array of dimension `ldb x n` with `ldb>=max(1,m)`.
ldb		input	leading dimension of two-dimensional array used to store matrix `B`.
beta	host	input	scalar used for multiplication, if `beta == 0` then `C` does not have to be a valid input.
C	host or device	in/out	array of dimension `ldc x n` with `ldc>=max(1,m)`.
ldc		input	leading dimension of two-dimensional array used to store matrix `C`.

The possible error values returned by this function and their meanings are listed below.

Error Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the operation completed successfully
`CUBLAS_STATUS_NOT_INITIALIZED`	the library was not initialized
`CUBLAS_STATUS_INVALID_VALUE`	the parameters `m,n<0`
`CUBLAS_STATUS_EXECUTION_FAILED`	the function failed to launch on the GPU

cublasXtsyrk()

cublasStatus_t cublasXtSsyrk(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,int n, int k,const float           *alpha,const float           *A, int lda,const float           *beta,float           *C, int ldc)
cublasStatus_t cublasXtDsyrk(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,int n, int k,const double          *alpha,const double          *A, int lda,const double          *beta,double          *C, int ldc)
cublasStatus_t cublasXtCsyrk(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,int n, int k,const cuComplex       *alpha,const cuComplex       *A, int lda,const cuComplex       *beta,cuComplex       *C, int ldc)
cublasStatus_t cublasXtZsyrk(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,int n, int k,const cuDoubleComplex *alpha,const cuDoubleComplex *A, int lda,const cuDoubleComplex *beta,cuDoubleComplex *C, int ldc)

此函数执行对称秩- K

Param.	Memory	In/out	Meaning
handle		input	handle to the cuBLASXt API context.
uplo		input	indicates if matrix `C` lower or upper part is stored, the other symmetric part is not referenced and is inferred from the stored elements.
trans		input	operation op(`A`) that is non- or transpose.
n		input	number of rows of matrix op(`A`) and `C`.
k		input	number of columns of matrix op(`A`).
alpha	host	input	scalar used for multiplication.
A	host or device	input	array of dimension `lda x k` with `lda>=max(1,n)` if `trans == CUBLAS_OP_N` and `lda x n` with `lda>=max(1,k)` otherwise.
lda		input	leading dimension of two-dimensional array used to store matrix A.
beta	host	input	scalar used for multiplication, if `beta==0` then `C` does not have to be a valid input.
C	host or device	in/out	array of dimension `ldc x n`, with `ldc>=max(1,n)`.
ldc		input	leading dimension of two-dimensional array used to store matrix `C`.

The possible error values returned by this function and their meanings are listed below.

Error Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the operation completed successfully
`CUBLAS_STATUS_NOT_INITIALIZED`	the library was not initialized
`CUBLAS_STATUS_INVALID_VALUE`	the parameters `n,k<0`
`CUBLAS_STATUS_EXECUTION_FAILED`	the function failed to launch on the GPU

cublasXtsyr2k()

cublasStatus_t cublasXtSsyr2k(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,size_t n, size_t k,const float           *alpha,const float           *A, size_t lda,const float           *B, size_t ldb,const float           *beta,float           *C, size_t ldc)
cublasStatus_t cublasXtDsyr2k(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,size_t n, size_t k,const double          *alpha,const double          *A, size_t lda,const double          *B, size_t ldb,const double          *beta,double          *C, size_t ldc)
cublasStatus_t cublasXtCsyr2k(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,size_t n, size_t k,const cuComplex       *alpha,const cuComplex       *A, size_t lda,const cuComplex       *B, size_t ldb,const cuComplex       *beta,cuComplex       *C, size_t ldc)
cublasStatus_t cublasXtZsyr2k(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,size_t n, size_t k,const cuDoubleComplex *alpha,const cuDoubleComplex *A, size_t lda,const cuDoubleComplex *B, size_t ldb,const cuDoubleComplex *beta,cuDoubleComplex *C, size_t ldc)

This function performs the symmetric rank- 2 update

Param.	Memory	In/out	Meaning
handle		input	handle to the cuBLASXt API context.
uplo		input	indicates if matrix `C` lower or upper part, is stored, the other symmetric part is not referenced and is inferred from the stored elements.
trans		input	operation op(`A`) that is non- or transpose.
n		input	number of rows of matrix op(`A`), op(`B`) and `C`.
k		input	number of columns of matrix op(`A`) and op(`B`).
alpha	host	input	scalar used for multiplication.
A	host or device	input	array of dimension `lda x k` with `lda>=max(1,n)` if `transa == CUBLAS_OP_N` and `lda x n` with `lda>=max(1,k)` otherwise.
lda		input	leading dimension of two-dimensional array used to store matrix `A`.
B	host or device	input	array of dimensions `ldb x k` with `ldb>=max(1,n)` if `transb == CUBLAS_OP_N` and `ldb x n` with `ldb>=max(1,k)` otherwise.
ldb		input	leading dimension of two-dimensional array used to store matrix `B`.
beta	host	input	scalar used for multiplication, if `beta==0`, then `C` does not have to be a valid input.
C	host or device	in/out	array of dimensions `ldc x n` with `ldc>=max(1,n)`.
ldc		input	leading dimension of two-dimensional array used to store matrix `C`.

The possible error values returned by this function and their meanings are listed below.

Error Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the operation completed successfully
`CUBLAS_STATUS_NOT_INITIALIZED`	the library was not initialized
`CUBLAS_STATUS_INVALID_VALUE`	the parameters `n,k<0`
`CUBLAS_STATUS_EXECUTION_FAILED`	the function failed to launch on the GPU

cublasXtsyrkx()

cublasStatus_t cublasXtSsyrkx(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,size_t n, size_t k,const float           *alpha,const float           *A, size_t lda,const float           *B, size_t ldb,const float           *beta,float           *C, size_t ldc)
cublasStatus_t cublasXtDsyrkx(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,size_t n, size_t k,const double          *alpha,const double          *A, size_t lda,const double          *B, size_t ldb,const double          *beta,double          *C, size_t ldc)
cublasStatus_t cublasXtCsyrkx(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,size_t n, size_t k,const cuComplex       *alpha,const cuComplex       *A, size_t lda,const cuComplex       *B, size_t ldb,const cuComplex       *beta,cuComplex       *C, size_t ldc)
cublasStatus_t cublasXtZsyrkx(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,size_t n, size_t k,const cuDoubleComplex *alpha,const cuDoubleComplex *A, size_t lda,const cuDoubleComplex *B, size_t ldb,const cuDoubleComplex *beta,cuDoubleComplex *C, size_t ldc)

This function performs a variation of the symmetric rank- k update

Param.	Memory	In/out	Meaning
handle		input	handle to the cuBLASXt API context.
uplo		input	indicates if matrix `C` lower or upper part, is stored, the other symmetric part is not referenced and is inferred from the stored elements.
trans		input	operation op(`A`) that is non- or transpose.
n		input	number of rows of matrix op(`A`), op(`B`) and `C`.
k		input	number of columns of matrix op(`A`) and op(`B`).
alpha	host	input	scalar used for multiplication.
A	host or device	input	array of dimension `lda x k` with `lda>=max(1,n)` if `transa == CUBLAS_OP_N` and `lda x n` with `lda>=max(1,k)` otherwise.
lda		input	leading dimension of two-dimensional array used to store matrix `A`.
B	host or device	input	array of dimensions `ldb x k` with `ldb>=max(1,n)` if `transb == CUBLAS_OP_N` and `ldb x n` with `ldb>=max(1,k)` otherwise.
ldb		input	leading dimension of two-dimensional array used to store matrix `B`.
beta	host	input	scalar used for multiplication, if `beta==0`, then `C` does not have to be a valid input.
C	host or device	in/out	array of dimensions `ldc x n` with `ldc>=max(1,n)`.
ldc		input	leading dimension of two-dimensional array used to store matrix `C`.

The possible error values returned by this function and their meanings are listed below.

Error Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the operation completed successfully
`CUBLAS_STATUS_NOT_INITIALIZED`	the library was not initialized
`CUBLAS_STATUS_INVALID_VALUE`	the parameters `n,k<0`
`CUBLAS_STATUS_EXECUTION_FAILED`	the function failed to launch on the GPU

cublasXtherk()

cublasStatus_t cublasXtCherk(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,int n, int k,const float  *alpha,const cuComplex       *A, int lda,const float  *beta,cuComplex       *C, int ldc)
cublasStatus_t cublasXtZherk(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,int n, int k,const double *alpha,const cuDoubleComplex *A, int lda,const double *beta,cuDoubleComplex *C, int ldc)

This function performs the Hermitian rank- K update

Param.	Memory	In/out	Meaning
handle		input	handle to the cuBLASXt API context.
uplo		input	indicates if matrix `A` lower or upper part is stored, the other Hermitian part is not referenced and is inferred from the stored elements.
trans		input	operation op(`A`) that is non- or (conj.) transpose.
n		input	number of rows of matrix op(`A`) and `C`.
k		input	number of columns of matrix op(`A`).
alpha	host	input	scalar used for multiplication.
A	host or device	input	array of dimension `lda x k` with `lda>=max(1,n)` if `transa == CUBLAS_OP_N` and `lda x n` with `lda>=max(1,k)` otherwise.
lda		input	leading dimension of two-dimensional array used to store matrix `A`.
beta	host	input	scalar used for multiplication, if `beta==0` then `C` does not have to be a valid input.
C	host or device	in/out	array of dimension `ldc x n`, with `ldc>=max(1,n)`. The imaginary parts of the diagonal elements are assumed and set to zero.
ldc		input	leading dimension of two-dimensional array used to store matrix `C`.

The possible error values returned by this function and their meanings are listed below.

Error Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the operation completed successfully
`CUBLAS_STATUS_NOT_INITIALIZED`	the library was not initialized
`CUBLAS_STATUS_INVALID_VALUE`	the parameters `n,k<0`
`CUBLAS_STATUS_EXECUTION_FAILED`	the function failed to launch on the GPU

cublasXther2k()

cublasStatus_t cublasXtCher2k(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,size_t n, size_t k,const cuComplex       *alpha,const cuComplex       *A, size_t lda,const cuComplex       *B, size_t ldb,const float  *beta,cuComplex       *C, size_t ldc)
cublasStatus_t cublasXtZher2k(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,size_t n, size_t k,const cuDoubleComplex *alpha,const cuDoubleComplex *A, size_t lda,const cuDoubleComplex *B, size_t ldb,const double *beta,cuDoubleComplex *C, size_t ldc)

此函数执行埃尔米特秩- 2 更新

Param.	Memory	In/out	Meaning
handle		input	handle to the cuBLASXt API context.
uplo		input	indicates if matrix `A` lower or upper part is stored, the other Hermitian part is not referenced and is inferred from the stored elements.
trans		input	operation op(`A`) that is non- or (conj.) transpose.
n		input	number of rows of matrix op(`A`), op(`B`) and `C`.
k		input	number of columns of matrix op(`A`) and op(`B`).
alpha	host	input	scalar used for multiplication.
A	host or device	input	array of dimension `lda x k` with `lda>=max(1,n)` if `transa == CUBLAS_OP_N` and `lda x n` with `lda>=max(1,k)` otherwise.
lda		input	leading dimension of two-dimensional array used to store matrix `A`.
B	host or device	input	array of dimension `ldb x k` with `ldb>=max(1,n)` if `transb == CUBLAS_OP_N` and `ldb x n` with `ldb>=max(1,k)` otherwise.
ldb		input	leading dimension of two-dimensional array used to store matrix `B`.
beta	host	input	scalar used for multiplication, if `beta==0` then `C` does not have to be a valid input.
C	host or device	in/out	array of dimension `ldc x n`, with `ldc>=max(1,n)`. The imaginary parts of the diagonal elements are assumed and set to zero.
ldc		input	leading dimension of two-dimensional array used to store matrix `C`.

The possible error values returned by this function and their meanings are listed below.

Error Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the operation completed successfully
`CUBLAS_STATUS_NOT_INITIALIZED`	the library was not initialized
`CUBLAS_STATUS_INVALID_VALUE`	the parameters `n,k<0`
`CUBLAS_STATUS_EXECUTION_FAILED`	the function failed to launch on the GPU

cublasXtherkx()

cublasStatus_t cublasXtCherkx(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,size_t n, size_t k,const cuComplex       *alpha,const cuComplex       *A, size_t lda,const cuComplex       *B, size_t ldb,const float  *beta,cuComplex       *C, size_t ldc)
cublasStatus_t cublasXtZherkx(cublasXtHandle_t handle,cublasFillMode_t uplo, cublasOperation_t trans,size_t n, size_t k,const cuDoubleComplex *alpha,const cuDoubleComplex *A, size_t lda,const cuDoubleComplex *B, size_t ldb,const double *beta,cuDoubleComplex *C, size_t ldc)

这个函数执行埃尔米特秩-x更新

Param.	Memory	In/out	Meaning
handle		input	handle to the cuBLASXt API context.
uplo		input	indicates if matrix `A` lower or upper part is stored, the other Hermitian part is not referenced and is inferred from the stored elements.
trans		input	operation op(`A`) that is non- or (conj.) transpose.
n		input	number of rows of matrix op(`A`), op(`B`) and `C`.
k		input	number of columns of matrix op(`A`) and op(`B`).
alpha	host	input	scalar used for multiplication.
A	host or device	input	array of dimension `lda x k` with `lda>=max(1,n)` if `transa == CUBLAS_OP_N` and `lda x n` with `lda>=max(1,k)` otherwise.
lda		input	leading dimension of two-dimensional array used to store matrix `A`.
B	host or device	input	array of dimension `ldb x k` with `ldb>=max(1,n)` if `transb == CUBLAS_OP_N` and `ldb x n` with `ldb>=max(1,k)` otherwise.
ldb		input	leading dimension of two-dimensional array used to store matrix `B`.
beta	host	input	real scalar used for multiplication, if `beta==0` then `C` does not have to be a valid input.
C	host or device	in/out	array of dimension `ldc x n`, with `ldc>=max(1,n)`. The imaginary parts of the diagonal elements are assumed and set to zero.
ldc		input	leading dimension of two-dimensional array used to store matrix `C`.

The possible error values returned by this function and their meanings are listed below.

Error Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the operation completed successfully
`CUBLAS_STATUS_NOT_INITIALIZED`	the library was not initialized
`CUBLAS_STATUS_INVALID_VALUE`	the parameters `n,k<0`
`CUBLAS_STATUS_EXECUTION_FAILED`	the function failed to launch on the GPU

cublasXttrsm()

cublasStatus_t cublasXtStrsm(cublasXtHandle_t handle,cublasSideMode_t side, cublasFillMode_t uplo,cublasOperation_t trans, cublasXtDiagType_t diag,size_t m, size_t n,const float           *alpha,const float           *A, size_t lda,float           *B, size_t ldb)
cublasStatus_t cublasXtDtrsm(cublasXtHandle_t handle,cublasSideMode_t side, cublasFillMode_t uplo,cublasOperation_t trans, cublasXtDiagType_t diag,size_t m, size_t n,const double          *alpha,const double          *A, size_t lda,double          *B, size_t ldb)
cublasStatus_t cublasXtCtrsm(cublasXtHandle_t handle,cublasSideMode_t side, cublasFillMode_t uplo,cublasOperation_t trans, cublasXtDiagType_t diag,size_t m, size_t n,const cuComplex       *alpha,const cuComplex       *A, size_t lda,cuComplex       *B, size_t ldb)
cublasStatus_t cublasXtZtrsm(cublasXtHandle_t handle,cublasSideMode_t side, cublasFillMode_t uplo,cublasOperation_t trans, cublasXtDiagType_t diag,size_t m, size_t n,const cuDoubleComplex *alpha,const cuDoubleComplex *A, size_t lda,cuDoubleComplex *B, size_t ldb)

This function solves the triangular linear system with multiple right-hand-sides

Param.	Memory	In/out	Meaning
handle		input	handle to the cuBLASXt API context.
side		input	indicates if matrix `A` is on the left or right of `X`.
uplo		input	indicates if matrix `A` lower or upper part is stored, the other part is not referenced and is inferred from the stored elements.
trans		input	operation op(`A`) that is non- or (conj.) transpose.
diag		input	indicates if the elements on the main diagonal of matrix `A` are unity and should not be accessed.
m		input	number of rows of matrix `B`, with matrix `A` sized accordingly.
n		input	number of columns of matrix `B`, with matrix `A` is sized accordingly.
alpha	host	input	scalar used for multiplication, if `alpha==0` then `A` is not referenced and `B` does not have to be a valid input.
A	host or device	input	array of dimension `lda x m` with `lda>=max(1,m)` if `side == CUBLAS_SIDE_LEFT` and `lda x n` with `lda>=max(1,n)` otherwise.
lda		input	leading dimension of two-dimensional array used to store matrix `A`.
B	host or device	in/out	array. It has dimensions `ldb x n` with `ldb>=max(1,m)`.
ldb		input	leading dimension of two-dimensional array used to store matrix `B`.

The possible error values returned by this function and their meanings are listed below.

Error Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the operation completed successfully
`CUBLAS_STATUS_NOT_INITIALIZED`	the library was not initialized
`CUBLAS_STATUS_INVALID_VALUE`	the parameters `m,n<0`
`CUBLAS_STATUS_EXECUTION_FAILED`	the function failed to launch on the GPU

cublasXttrmm()

cublasStatus_t cublasXtStrmm(cublasXtHandle_t handle,cublasSideMode_t side, cublasFillMode_t uplo,cublasOperation_t trans, cublasDiagType_t diag,size_t m, size_t n,const float           *alpha,const float           *A, size_t lda,const float           *B, size_t ldb,float                 *C, size_t ldc)
cublasStatus_t cublasXtDtrmm(cublasXtHandle_t handle,cublasSideMode_t side, cublasFillMode_t uplo,cublasOperation_t trans, cublasDiagType_t diag,size_t m, size_t n,const double          *alpha,const double          *A, size_t lda,const double          *B, size_t ldb,double                *C, size_t ldc)
cublasStatus_t cublasXtCtrmm(cublasXtHandle_t handle,cublasSideMode_t side, cublasFillMode_t uplo,cublasOperation_t trans, cublasDiagType_t diag,size_t m, size_t n,const cuComplex       *alpha,const cuComplex       *A, size_t lda,const cuComplex       *B, size_t ldb,cuComplex             *C, size_t ldc)
cublasStatus_t cublasXtZtrmm(cublasXtHandle_t handle,cublasSideMode_t side, cublasFillMode_t uplo,cublasOperation_t trans, cublasDiagType_t diag,size_t m, size_t n,const cuDoubleComplex *alpha,const cuDoubleComplex *A, size_t lda,const cuDoubleComplex *B, size_t ldb,cuDoubleComplex       *C, size_t ldc)

此函数执行三角矩阵-矩阵乘法

Param.	Memory	In/out	Meaning
handle		input	handle to the cuBLASXt API context.
side		input	indicates if matrix `A` is on the left or right of `B`.
uplo		input	indicates if matrix `A` lower or upper part is stored, the other part is not referenced and is inferred from the stored elements.
trans		input	operation op(`A`) that is non- or (conj.) transpose.
diag		input	indicates if the elements on the main diagonal of matrix `A` are unity and should not be accessed.
m		input	number of rows of matrix `B`, with matrix `A` sized accordingly.
n		input	number of columns of matrix `B`, with matrix `A` sized accordingly.
alpha	host	input	scalar used for multiplication, if `alpha==0` then `A` is not referenced and `B` does not have to be a valid input.
A	host or device	input	array of dimension `lda x m` with `lda>=max(1,m)` if `side == CUBLAS_SIDE_LEFT` and `lda x n` with `lda>=max(1,n)` otherwise.
lda		input	leading dimension of two-dimensional array used to store matrix `A`.
B	host or device	input	array of dimension `ldb x n` with `ldb>=max(1,m)`.
ldb		input	leading dimension of two-dimensional array used to store matrix `B`.
C	host or device	in/out	array of dimension `ldc x n` with `ldc>=max(1,m)`.
ldc		input	leading dimension of two-dimensional array used to store matrix `C`.

The possible error values returned by this function and their meanings are listed below.

Error Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the operation completed successfully
`CUBLAS_STATUS_NOT_INITIALIZED`	the library was not initialized
`CUBLAS_STATUS_INVALID_VALUE`	the parameters `m,n<0`
`CUBLAS_STATUS_EXECUTION_FAILED`	the function failed to launch on the GPU

cublasXtspmm()

cublasStatus_t cublasXtSspmm( cublasXtHandle_t handle,cublasSideMode_t side,cublasFillMode_t uplo,size_t m,size_t n,const float *alpha,const float *AP,const float *B,size_t ldb,const float *beta,float *C,size_t ldc );cublasStatus_t cublasXtDspmm( cublasXtHandle_t handle,cublasSideMode_t side,cublasFillMode_t uplo,size_t m,size_t n,const double *alpha,const double *AP,const double *B,size_t ldb,const double *beta,double *C,size_t ldc );cublasStatus_t cublasXtCspmm( cublasXtHandle_t handle,cublasSideMode_t side,cublasFillMode_t uplo,size_t m,size_t n,const cuComplex *alpha,const cuComplex *AP,const cuComplex *B,size_t ldb,const cuComplex *beta,cuComplex *C,size_t ldc );cublasStatus_t cublasXtZspmm( cublasXtHandle_t handle,cublasSideMode_t side,cublasFillMode_t uplo,size_t m,size_t n,const cuDoubleComplex *alpha,const cuDoubleComplex *AP,const cuDoubleComplex *B,size_t ldb,const cuDoubleComplex *beta,cuDoubleComplex *C,size_t ldc );

This function performs the symmetric packed matrix-matrix multiplication

Param.	Memory	In/out	Meaning
handle		input	handle to the cuBLASXt API context.
side		input	indicates if matrix `A` is on the left or right of `B`.
uplo		input	indicates if matrix `A` lower or upper part is stored, the other symmetric part is not referenced and is inferred from the stored elements.
m		input	number of rows of matrix `A` and `B`, with matrix `A` sized accordingly.
n		input	number of columns of matrix `C` and `A`, with matrix `A` sized accordingly.
alpha	host	input	scalar used for multiplication.
AP	host	input	array with � stored in packed format.
B	host or device	input	array of dimension `ldb x n` with `ldb>=max(1,m)`.
ldb		input	leading dimension of two-dimensional array used to store matrix `B`.
beta	host	input	scalar used for multiplication, if `beta == 0` then `C` does not have to be a valid input.
C	host or device	in/out	array of dimension `ldc x n` with `ldc>=max(1,m)`.
ldc		input	leading dimension of two-dimensional array used to store matrix `C`.

The possible error values returned by this function and their meanings are listed below.

Error Value	Meaning
`CUBLAS_STATUS_SUCCESS`	the operation completed successfully
`CUBLAS_STATUS_NOT_INITIALIZED`	the library was not initialized
`CUBLAS_STATUS_INVALID_VALUE`	the parameters `m,n<0`
`CUBLAS_STATUS_NOT_SUPPORTED`	the matrix AP is located on a GPU device
`CUBLAS_STATUS_EXECUTION_FAILED`	the function failed to launch on the GPU

词库加载错误:未能找到文件“E:\highferrum_mysql\Configuration\Dict_Stopwords.txt”。

上一篇：探索LeetCode【0002】两数相加

下一篇：君乐宝简醇，引领酸奶新一轮迭代君乐宝酸奶和简醇系列区别君乐宝简醇酸奶的优缺点

cuBALS使用（5）-cublasXt

平铺设计方法

Hybrid CPU-GPU computation

Results reproducibility

cuBLASXt API数据类型

cublasXtHandle_ t

cublasXtOpType_t

cublasXtBlasOp_t

cublasXtSetCpuRoutine

cublasXtPinningMemMode_t

cuBLASXt API Helper Function Reference

cublasXtCreate()

cublasXtDestroy()

cublasXtDeviceSelect()

cublasXtSetBlockDim()

cublasXtGetBlockDim()

cublasXtSetCpuRoutine()

cublasXtSetCpuRatio()

cublasXtSetPinningMemMode()

cublasXtGetPinningMemMode()

cuBLASXt API Math Functions Reference

cublasXtgemm()

cublasXthemm()

cublasXtsymm()

cublasXtsyrk()

cublasXtsyr2k()

cublasXtsyrkx()

cublasXtherk()

cublasXther2k()

cublasXtherkx()

cublasXttrsm()

cublasXttrmm()

cublasXtspmm()

相关内容

热门资讯