IP PortfolioCompute acceleratorshpc

of_acc_blas

BLAS engine

Maturity plannedTargets FPGA + ASICDifficulty HardPriority 2

FP64 and FP32 engine for BLAS level 1, 2 and 3 kernels (AXPY, GEMV, GEMM, TRSM) with blocked operand buffers.

Planned. This block is specified in the catalog with its interfaces and targets. No implementation exists yet; the skeleton command below generates a lint-clean shell with its ports and registers.

Interfaces

PortDirectionKindWidthNotes
ctrlin/outAXI4-Lite control bus32Control and status registers, including ID, VERSION and STATUS
irqoutinterrupt1Interrupt request

Standards

  • BLAS
  • IEEE 754-2019

More in hpc

IDBlockMaturity
of_acc_fftStreaming FFT enginesimulated
of_acc_spmv_graphSparse matrix and graph engineplanned
of_acc_stencilStencil computation engineplanned
of_acc_md_forcesMolecular dynamics force pipelineplanned
of_acc_monte_carloMonte Carlo engineplanned
of_acc_seq_alignSequence alignment engineplanned
of_acc_matrix_decompMatrix decomposition engineplanned
of_acc_sortSorting engineplanned
of_acc_isingDigital annealerplanned
of_acc_cgraCoarse-grained reconfigurable arrayplanned