Re:BOOM v2: an open-source out-of-order RISC-V core
by rjsw on Tuesday September 26, 2017 @07:26PM
(#15343545)
Other people have pointed out that Itanium is the most recent example of a project that expected to be able to write a really smart compiler for an in-order CPU and failed.
If you can write better LLVM plugins then I'm sure Intel and HP will be happy to throw lots of money in your direction.
Re:BOOM v2: an open-source out-of-order RISC-V core
by dnautics on Tuesday September 26, 2017 @07:33PM
(#15343594)
The field is littered with the tombstones of people that have tried to make compilers for insert any foreign architecture. Obviously in-order CPUs are a challenge on top of that. I do think there is a real 'go-to-market' problem. If you think about it this is kind of solved by Nvidia (with CUDA). GPUs are in-order computational arrays with custom compiler.
Re:BOOM v2: an open-source out-of-order RISC-V core
by wbl on Tuesday September 26, 2017 @09:01PM
(#15344063)
GPUs are vector processors under another name, that hide the latency of memory differently. They don't need to use the sort of compiler tricks you would with CPU code.
Re:BOOM v2: an open-source out-of-order RISC-V core
by deepnotderp on Wednesday September 27, 2017 @01:33AM
(#15345151)
Yeah, but GPUs target only a small subset of the workloads and they are very hard to program even then. I prefer processors like the Rex Neo or Adapteva Epiphany in that respect actually.
Re:BOOM v2: an open-source out-of-order RISC-V core
by dnautics on Wednesday September 27, 2017 @02:42AM
(#15345408)
have you tried programming rex neo?
Re:BOOM v2: an open-source out-of-order RISC-V core
by deepnotderp on Wednesday September 27, 2017 @02:53AM
(#15345452)
Nope, I know you have experience with it though, so perhaps you can help there ;)
I've toyed around with the older Epiphanies though, and they were definitely easier than GPUs in many respects.
Re:BOOM v2: an open-source out-of-order RISC-V core
by AlphaSite on Tuesday September 26, 2017 @09:54PM
(#15344280)
Also, as I understand it, GPUs are now out of order as well, aren’t they?
Re:BOOM v2: an open-source out-of-order RISC-V core
by TomV1971 on Tuesday September 26, 2017 @11:32PM
(#15344714)
No, they are not.
OoO is much more expensive to implement than simply scheduling a different warp to hide latency.
Re:BOOM v2: an open-source out-of-order RISC-V core
by deepnotderp on Wednesday September 27, 2017 @01:27AM
(#15345139)
Absolutely not.
Maybe you're confusing the GPU's threading techniques for OoO?
Nowithstanding the fact that your answer is totally unhelpful: I thought about it for a second and I think the answer is basically that if you have a multithreading cores and you're pending on the results of another operation, then you can't necessarily know what optimizations you can do ahead of time because you don't know what other threads are resident on your core, which will affect the on-the-fly reorganization.