Embedded systems frequently use FPGAs to perform highly parallel data processing tasks. However, building such a system usually requires specialized hardware design skills with VHDL or Verilog. Instead, this paper presents the VectorBlox MXP Matrix Processor, an FPGA-based soft processor capable of highly parallel execution. Programmed entirely in C, the MXP is capable of executing dataparallel software algorithms at hardware-like speeds. For example, the MXP running at 200MHz or higher can implement a multi-tap FIR filter and output 1 element per clock cycle. MXP's parameterized design lets the user specify the amount of parallelism required, ranging from 1 to 128 or more parallel ALUs. Key features of the MXP include a parallel-access scratchpad memory to hold vector data and high-throughput DMA and scatter/gather engines. To provide extreme performance, the processor is expandable with custom vector instructions and custom DMA filters. Finally, the MXP seamlessly ties into existing Altera and Xilinx development flows, simplifying system creation and deployment.

Abstract-This paper presents VENICE, a new soft vector processor (SVP) for FPGA applications. VENICE differs from previous SVPs in that it was designed for maximum throughput with a small number (1 to 4) of ALUs. By increasing clockspeed and eliminating bottlenecks in ALU utilization, VENICE can achieve over 2x better performance-per-logic block than VEGAS, the previous best SVP. While VENICE can scale to a large number of ALUs, a multiprocessor system of smaller VENICE SVPs is shown to scale better for benchmarks with limited innerloop parallelism. VENICE is also simpler to program, as its instructions use standard C pointers into a scratchpad memory rather than vector registers.

Abstract-This paper presents VENICE, a new soft vector processor (SVP) for FPGA applications. VENICE differs from previous SVPs in that it was designed for maximum throughput with a small number (1 to 4) of ALUs. By increasing clockspeed and eliminating bottlenecks in ALU utilization, VENICE can achieve over 2x better performance-per-logic block than VEGAS, the previous best SVP. While VENICE can scale to a large number of ALUs, a multiprocessor system of smaller VENICE SVPs is shown to scale better for benchmarks with limited innerloop parallelism. VENICE is also simpler to program, as its instructions use standard C pointers into a scratchpad memory rather than vector registers.

Soft vector processors (SVPs) achieve significant performance gains through the use of parallel ALUs. However, since ALUs are used in a time-multiplexed fashion, this does not exploit a key strength of FPGA performance: pipeline parallelism. This paper shows how streaming pipelines can be integrated into the datapath of a SVP to achieve dramatic speedups. The SVP plays an important role in supplying the pipeline with high-bandwidth input data and storing its results using on-chip memory. However, the SVP must also perform the housekeeping tasks necessary to keep the pipeline busy. In particular, it orchestrates data movement between on-chip memory and external DRAM, it pre-or post-processes the data using its own ALUs, and it controls the overall sequence of execution. Since the SVP is programmed in C, these tasks are easier to develop and debug than using a traditional HDL approach. Using the N-body problem as a case study, this paper illustrates how custom streaming pipelines are integrated into the SVP datapath and multiple techniques for generating them. Using a custom pipeline, we demonstrate speedups over 7,000 times and performance-per-ALM over 100 times better than Nios II/f. The custom pipeline is also 50 times faster than a naive Intel Core i7 processor implementation.