News for hackers. Stuff that matters.
Re:How many 32-bit RISC CPUs fit in an FPGA? Now vs. 1995? by justincormack on Thursday March 27, 2014 @08:22PM (#7484450)
The GPU vendors dont exactly have open toolchains either. OpenCL is not open in that we get to write assembler for the GPU... It is only a little better.

But GPUs got shipped in volume. I think they were just cheaper for the performance level.

Re:How many 32-bit RISC CPUs fit in an FPGA? Now vs. 1995? by axman6 on Thursday March 27, 2014 @09:02PM (#7484626)
Not sure how relevant it is, but isn't PTX available through LLVM?
Re:How many 32-bit RISC CPUs fit in an FPGA? Now vs. 1995? by sparky on Friday March 28, 2014 @10:39AM (#7487514)
LLVM has an open-source PTX backend, and newer versions of the official CUDA compiler use LLVM to generate PTX internally, but PTX is a device-independent intermediate layer, and the PTX-to-SASS compiler is closed-source.