Хабр Курсы для всех
РЕКЛАМА
Практикум, Хекслет, SkyPro, авторские курсы — собрали всех и попросили скидки. Осталось выбрать!
с кучей никем так и нереализованный математических фич
что стоит T-Buffer на VSA-100 (Voodoo4/5), дающий FSAA, Blur и переменный фокус, а те самые мат. навороты по крутизне дали бы прикурить этим вашим шейдерам
У Mojo ожидалось кардинальное новшество — реализация некой разновидности аппаратной сортировки, <...>
Т.е, подаваемые на ускоритель треугольники аппаратно сортировались бы прямо на лету, за счет определения принадлежащих им тайлов
игровые видеокарты — это урезанные (по скорости отрисовки сложных моделей) профессиональные
они на одинаковом чип
Но если вы внедрите в игру свою модель с миллионами треугольников
А стоимость Квадры в 5 раз больше Жефорса.
В итоге драйвер включает фичи, которые для более дешевой GeForce на включал.
Ускорения при это НЕ происходит.
Просто Вы хотите во что бы то ни было доказать мне свою правоту.
Производители AMD и Nvidia достаточно жестко держат рынок
MIAOW (pronounced me-ow) is an open source GPU created by the Vertical Research Group at the University of Wisconsin-Madison led by Professor Karu Sankaralingam. Based off of the publicly released Southern Islands ISA by AMD, MIAOW implements a compute unit suitable for performing architecture analysis and experimentation with GPGPU workloads. In addition to the Verilog HDL composing the compute unit, MIAOW also includes a suite of unit tests and benchmarks for regression testing.
A primary motivator for MIAOW's creation is the belief that software simulators of hardware such as CPUs and GPUs often miss many subtle aspects that can skew the performance, power, and other quantitative results that they produce. As an actual implementation of a GPU's logic, the Vertical Research Group believes that MIAOW can be a useful tool in producing not only more accurate quantitative results when benchmarking GPGPU workloads but also provide context for the architectural complexities of actually implementing newly proposed algorithms and designs that are intended to improve performance or other desired characteristics.
Our long term vision is to move forward the movement of Open Source Hardware by contributing an open source GPU implementation to it.
It must be emphasized that MIAOW represents a GPU's compute unit. It does not possess the auxiliary logic required to produce actual graphical output nor does it have logic to connect it to a specific memory interface or system bus. These extensions can be developed and we would welcome outside contributors for such efforts, but as MIAOW was created as a research tool their presence was not an absolute necessity in running benchmarks and experiments.
MIAOW is licensed under the 3-clause BSD license.
MIAOW's RTL and detailed documetation are on Github. A short whitepaper that decsribes MIAOW and its usage in research is here
This project is a open source processor designed for highly parallel and GPGPU applications. It was inspired by Intel's Larrabee, although the instruction set and microarchitecture are substantially different.
The processor runs in Verilog simulation and on FPGA. It is a modern architecture, with set associative L1 & L2 caches, fine grained hardware multi-threading, pipelined SIMD floating point and integer execution units, and support for multiple cache coherent cores. It includes a C/C++ compiler based on LLVM
This video shows a software renderer written in C++ rendering a Phong shaded teapot with 2300 triangles. It is running on a single core at 50Mhz on a Cyclone IV FPGA.
Проект open source GPU на Kickstarter