文件列表:

hw-nvdlav1 (0, 2018-04-19)
hw-nvdlav1\LICENSE (10504, 2018-04-19)
hw-nvdlav1\Makefile (4163, 2018-04-19)
hw-nvdlav1\VERSION (17, 2018-04-19)
hw-nvdlav1\cmod (0, 2018-04-19)
hw-nvdlav1\cmod\Makefile (5854, 2018-04-19)
hw-nvdlav1\cmod\bdma (0, 2018-04-19)
hw-nvdlav1\cmod\bdma\BdmaCore.cpp (26373, 2018-04-19)
hw-nvdlav1\cmod\bdma\BdmaCore.h (8800, 2018-04-19)
hw-nvdlav1\cmod\bdma\NV_NVDLA_bdma.cpp (6657, 2018-04-19)
hw-nvdlav1\cmod\bdma\NV_NVDLA_bdma.h (3806, 2018-04-19)
hw-nvdlav1\cmod\bdma\gen (0, 2018-04-19)
hw-nvdlav1\cmod\bdma\gen\NV_NVDLA_bdma_bdma_gen.h (2516, 2018-04-19)
hw-nvdlav1\cmod\bdma\gen\bdma_reg_model.cpp (7133, 2018-04-19)
hw-nvdlav1\cmod\bdma\gen\bdma_reg_model.h (3374, 2018-04-19)
hw-nvdlav1\cmod\bdma\gen\bdmacoreconfigclass.h (2242, 2018-04-19)
hw-nvdlav1\cmod\cacc (0, 2018-04-19)
hw-nvdlav1\cmod\cacc\NV_NVDLA_cacc.cpp (79337, 2018-04-19)
hw-nvdlav1\cmod\cacc\NV_NVDLA_cacc.h (9679, 2018-04-19)
hw-nvdlav1\cmod\cacc\gen (0, 2018-04-19)
hw-nvdlav1\cmod\cacc\gen\NV_NVDLA_cacc_cacc_gen.h (2535, 2018-04-19)
hw-nvdlav1\cmod\cacc\gen\cacc_reg_model.cpp (7334, 2018-04-19)
hw-nvdlav1\cmod\cacc\gen\cacc_reg_model.h (3399, 2018-04-19)
hw-nvdlav1\cmod\cbuf (0, 2018-04-19)
hw-nvdlav1\cmod\cbuf\NV_NVDLA_cbuf.cpp (7816, 2018-04-19)
hw-nvdlav1\cmod\cbuf\NV_NVDLA_cbuf.h (3105, 2018-04-19)
hw-nvdlav1\cmod\cdma (0, 2018-04-19)
hw-nvdlav1\cmod\cdma\NV_NVDLA_cdma.cpp (223664, 2018-04-19)
hw-nvdlav1\cmod\cdma\NV_NVDLA_cdma.h (16505, 2018-04-19)
hw-nvdlav1\cmod\cdma\gen (0, 2018-04-19)
hw-nvdlav1\cmod\cdma\gen\NV_NVDLA_cdma_cdma_gen.h (2535, 2018-04-19)
hw-nvdlav1\cmod\cdma\gen\cdma_reg_model.cpp (13054, 2018-04-19)
hw-nvdlav1\cmod\cdma\gen\cdma_reg_model.h (5899, 2018-04-19)
hw-nvdlav1\cmod\cdp (0, 2018-04-19)
hw-nvdlav1\cmod\cdp\NV_NVDLA_cdp.cpp (79706, 2018-04-19)
hw-nvdlav1\cmod\cdp\NV_NVDLA_cdp.h (8516, 2018-04-19)
hw-nvdlav1\cmod\cdp\gen (0, 2018-04-19)
... ...

# NVDLA Open Source Hardware, version 1.0 --- ## NVDLA The NVIDIA Deep Learning Accelerator (NVDLA) is a free and open architecture that promotes a standard way to design deep learning inference accelerators. With its modular architecture, NVDLA is scalable, highly configurable, and designed to simplify integration and portability. Learn more about NVDLA on the project web page. ## About this release This release, in the `nvdlav1` branch, contains the non-configurable "full-precision" version of NVDLA. This non-configurable version is fixed at 2048 8-bit MACs (or 1024 16-bit fixed- or floating-point MACs). This branch is expected to be a stable sustaining release; although bug fixes may be added, new RTL feature improvements will not appear in this branch. Additionally, this branch will diverge from the `master` branch; commits from that branch may be cherry-picked into this branch, but wholesale merges from `master` will not appear on `nvdlav1`. ## Online Documentation NVDLA documentation is located [here](http://nvdla.org/contents.html). Hardware specific documentation is located at the following pages. * [Hardware Architecture](http://nvdla.org/hwarch.html). * [Integrator's Manual](http://nvdla.org/integration_guide.html). This README file contains only basic information. ## Directory Structure This repository contains the RTL, C-model, and testbench code associated with the NVDLA hardware release. In this repository, you will find: * vmod/ -- RTL model, including: * vmod/nvdla/ -- Verilog implementation of NVDLA * vmod/vlibs/ -- library and cell models * vmod/rams/ -- behavioral models of RAMs used by NVDLA * syn/ -- example synthesis scripts for NVDLA * perf/ -- performance estimator spreadsheet for NVDLA * verif/ -- trace-player testbench for basic sanity validation * verif/traces/ -- sample traces associated with various networks * tools -- tools used for building the RTL and running simulation/synthesis/etc. * spec -- RTL configuration option settings. ## Building the NVDLA Hardware See the [integrator's manual](http://nvdla.org/integration_guide.html) for more information on the setup and other build commands and options. The basic build command to compile the design and run a short sanity simulation is: bin/tmake

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：