Developer Guide and Reference

  • 2022.1
  • 04/11/2022
  • Public Content
Contents

Threadpool interoperability API

Overview

API extensions to interact with the underlying Threadpool run-time. More…
// namespaces namespace dnnl::threadpool_interop; // global functions dnnl_status_t DNNL_API dnnl_threadpool_interop_stream_create( dnnl_stream_t* stream, dnnl_engine_t engine, void* threadpool ); dnnl_status_t DNNL_API dnnl_threadpool_interop_stream_get_threadpool( dnnl_stream_t astream, void** threadpool ); dnnl_status_t DNNL_API dnnl_threadpool_interop_sgemm( char transa, char transb, dnnl_dim_t M, dnnl_dim_t N, dnnl_dim_t K, float alpha, const float* A, dnnl_dim_t lda, const float* B, dnnl_dim_t ldb, float beta, float* C, dnnl_dim_t ldc, void* threadpool ); dnnl_status_t DNNL_API dnnl_threadpool_interop_gemm_u8s8s32( char transa, char transb, char offsetc, dnnl_dim_t M, dnnl_dim_t N, dnnl_dim_t K, float alpha, const uint8_t* A, dnnl_dim_t lda, uint8_t ao, const int8_t* B, dnnl_dim_t ldb, int8_t bo, float beta, int32_t* C, dnnl_dim_t ldc, const int32_t* co, void* threadpool ); dnnl_status_t DNNL_API dnnl_threadpool_interop_gemm_s8s8s32( char transa, char transb, char offsetc, dnnl_dim_t M, dnnl_dim_t N, dnnl_dim_t K, float alpha, const int8_t* A, dnnl_dim_t lda, int8_t ao, const int8_t* B, dnnl_dim_t ldb, int8_t bo, float beta, int32_t* C, dnnl_dim_t ldc, const int32_t* co, void* threadpool );

Detailed Documentation

API extensions to interact with the underlying Threadpool run-time.
Global Functions
dnnl_status_t DNNL_API dnnl_threadpool_interop_stream_create( dnnl_stream_t* stream, dnnl_engine_t engine, void* threadpool )
Creates an execution stream with specified threadpool.
Parameters:
stream
Output execution stream.
engine
Engine to create the execution stream on.
threadpool
Pointer to an instance of a C++ class that implements dnnl::threapdool_iface interface.
Returns:
dnnl_success on success and a status describing the error otherwise.
See also:
dnnl_status_t DNNL_API dnnl_threadpool_interop_stream_get_threadpool( dnnl_stream_t astream, void** threadpool )
Returns a threadpool to be used by the execution stream.
Parameters:
astream
Execution stream.
threadpool
Output pointer to an instance of a C++ class that implements dnnl::threapdool_iface interface. Set to NULL if the stream was created without threadpool.
Returns:
dnnl_success on success and a status describing the error otherwise.
See also:
dnnl_status_t DNNL_API dnnl_threadpool_interop_sgemm( char transa, char transb, dnnl_dim_t M, dnnl_dim_t N, dnnl_dim_t K, float alpha, const float* A, dnnl_dim_t lda, const float* B, dnnl_dim_t ldb, float beta, float* C, dnnl_dim_t ldc, void* threadpool )
Performs single-precision matrix-matrix multiply.
The operation is defined as:
C := alpha * op( A ) * op( B ) + beta * C
where
  • op( X ) = X
    or
    op( X ) = X**T
    ,
  • alpha
    and
    beta
    are scalars, and
  • A
    ,
    B
    , and
    C
    are matrices:
    • op( A )
      is an
      MxK
      matrix,
    • op( B )
      is an
      KxN
      matrix,
    • C
      is an
      MxN
      matrix.
The matrices are assumed to be stored in row-major order (the elements in each of the matrix rows are contiguous in memory).
This API does not support XERBLA. Instead, unlike the standard BLAS functions, this one returns a dnnl_status_t value to allow error handling.
Parameters:
transa
Transposition flag for matrix A: ‘N’ or ‘n’ means A is not transposed, and ‘T’ or ‘t’ means that A is transposed.
transb
Transposition flag for matrix B: ‘N’ or ‘n’ means B is not transposed, and ‘T’ or ‘t’ means that B is transposed.
M
The M dimension.
N
The N dimension.
K
The K dimension.
alpha
The alpha parameter that is used to scale the product of matrices A and B.
A
A pointer to the A matrix data.
lda
The leading dimension for the matrix A.
B
A pointer to the B matrix data.
ldb
The leading dimension for the matrix B.
beta
The beta parameter that is used to scale the matrix C.
C
A pointer to the C matrix data.
ldc
The leading dimension for the matrix C.
threadpool
A pointer to a threadpool interface (only when built with the THREADPOOL CPU runtime).
Returns:
dnnl_success / dnnl::status::success on success and a status describing the error otherwise.
dnnl_status_t DNNL_API dnnl_threadpool_interop_gemm_u8s8s32( char transa, char transb, char offsetc, dnnl_dim_t M, dnnl_dim_t N, dnnl_dim_t K, float alpha, const uint8_t* A, dnnl_dim_t lda, uint8_t ao, const int8_t* B, dnnl_dim_t ldb, int8_t bo, float beta, int32_t* C, dnnl_dim_t ldc, const int32_t* co, void* threadpool )
Performs integer matrix-matrix multiply on 8-bit unsigned matrix A, 8-bit signed matrix B, and 32-bit signed resulting matrix C.
The operation is defined as:
C := alpha * (op(A) - A_offset) * (op(B) - B_offset) + beta * C + C_offset
where
  • op( X ) = X
    or
    op( X ) = X**T
    ,
  • alpha
    and
    beta
    are scalars, and
  • A
    ,
    B
    , and
    C
    are matrices:
    • op( A )
      is an
      MxK
      matrix,
    • op( B )
      is an
      KxN
      matrix,
    • C
      is an
      MxN
      matrix.
  • A_offset
    is an
    MxK
    matrix with every element equal the
    ao
    value,
  • B_offset
    is an
    KxN
    matrix with every element equal the
    bo
    value,
  • C_offset
    is an
    MxN
    matrix which is defined by the
    co
    array of size
    len
    :
    • if
      offsetc = F
      : the
      len
      must be at least
      1
      ,
    • if
      offsetc = C
      : the
      len
      must be at least
      max(1, m)
      ,
    • if
      offsetc = R
      : the
      len
      must be at least
      max(1, n)
      ,
The matrices are assumed to be stored in row-major order (the elements in each of the matrix rows are contiguous in memory).
This API does not support XERBLA. Instead, unlike the standard BLAS functions, this one returns a dnnl_status_t value to allow error handling.
On some architectures saturation may happen during intermediate computations, which would lead to unexpected results. For more details, refer to Nuances of int8 Computations.
Parameters:
transa
Transposition flag for matrix A: ‘N’ or ‘n’ means A is not transposed, and ‘T’ or ‘t’ means that A is transposed.
transb
Transposition flag for matrix B: ‘N’ or ‘n’ means B is not transposed, and ‘T’ or ‘t’ means that B is transposed.
offsetc
Flag specifying how offsets should be applied to matrix C:
  • ‘F’ means that the same offset will be applied to each element of the matrix C,
  • ‘C’ means that individual offset will be applied to each element within each column,
  • ‘R’ means that individual offset will be applied to each element within each row.
M
The M dimension.
N
The N dimension.
K
The K dimension.
alpha
The alpha parameter that is used to scale the product of matrices A and B.
A
A pointer to the A matrix data.
lda
The leading dimension for the matrix A.
ao
The offset value for the matrix A.
B
A pointer to the B matrix data.
ldb
The leading dimension for the matrix B.
bo
The offset value for the matrix B.
beta
The beta parameter that is used to scale the matrix C.
C
A pointer to the C matrix data.
ldc
The leading dimension for the matrix C.
co
An array of offset values for the matrix C. The number of elements in the array depends on the value of
offsetc
.
threadpool
A pointer to a threadpool interface (only when built with the THREADPOOL CPU runtime).
Returns:
dnnl_success / dnnl::status::success on success and a status describing the error otherwise.
dnnl_status_t DNNL_API dnnl_threadpool_interop_gemm_s8s8s32( char transa, char transb, char offsetc, dnnl_dim_t M, dnnl_dim_t N, dnnl_dim_t K, float alpha, const int8_t* A, dnnl_dim_t lda, int8_t ao, const int8_t* B, dnnl_dim_t ldb, int8_t bo, float beta, int32_t* C, dnnl_dim_t ldc, const int32_t* co, void* threadpool )
Performs integer matrix-matrix multiply on 8-bit signed matrix A, 8-bit signed matrix B, and 32-bit signed resulting matrix C.
The operation is defined as:
C := alpha * (op(A) - A_offset) * (op(B) - B_offset) + beta * C + C_offset
where
  • op( X ) = X
    or
    op( X ) = X**T
    ,
  • alpha
    and
    beta
    are scalars, and
  • A
    ,
    B
    , and
    C
    are matrices:
    • op( A )
      is an
      MxK
      matrix,
    • op( B )
      is an
      KxN
      matrix,
    • C
      is an
      MxN
      matrix.
  • A_offset
    is an
    MxK
    matrix with every element equal the
    ao
    value,
  • B_offset
    is an
    KxN
    matrix with every element equal the
    bo
    value,
  • C_offset
    is an
    MxN
    matrix which is defined by the
    co
    array of size
    len
    :
    • if
      offsetc = F
      : the
      len
      must be at least
      1
      ,
    • if
      offsetc = C
      : the
      len
      must be at least
      max(1, m)
      ,
    • if
      offsetc = R
      : the
      len
      must be at least
      max(1, n)
      ,
The matrices are assumed to be stored in row-major order (the elements in each of the matrix rows are contiguous in memory).
This API does not support XERBLA. Instead, unlike the standard BLAS functions, this one returns a dnnl_status_t value to allow error handling.
On some architectures saturation may happen during intermediate computations, which would lead to unexpected results. For more details, refer to Nuances of int8 Computations.
Parameters:
transa
Transposition flag for matrix A: ‘N’ or ‘n’ means A is not transposed, and ‘T’ or ‘t’ means that A is transposed.
transb
Transposition flag for matrix B: ‘N’ or ‘n’ means B is not transposed, and ‘T’ or ‘t’ means that B is transposed.
offsetc
Flag specifying how offsets should be applied to matrix C:
  • ‘F’ means that the same offset will be applied to each element of the matrix C,
  • ‘C’ means that individual offset will be applied to each element within each column,
  • ‘R’ means that individual offset will be applied to each element within each row.
M
The M dimension.
N
The N dimension.
K
The K dimension.
alpha
The alpha parameter that is used to scale the product of matrices A and B.
A
A pointer to the A matrix data.
lda
The leading dimension for the matrix A.
ao
The offset value for the matrix A.
B
A pointer to the B matrix data.
ldb
The leading dimension for the matrix B.
bo
The offset value for the matrix B.
beta
The beta parameter that is used to scale the matrix C.
C
A pointer to the C matrix data.
ldc
The leading dimension for the matrix C.
co
An array of offset values for the matrix C. The number of elements in the array depends on the value of
offsetc
.
threadpool
A pointer to a threadpool interface (only when built with the THREADPOOL CPU runtime).
Returns:
dnnl_success / dnnl::status::success on success and a status describing the error otherwise.

Product and Performance Information

1

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.