Any updates regarding opensource and HD5870?
Is it possible to improve the driver if we provide Marek full ssh to machine with GPU in question? Or perhaps any other method of remote access? :/
The results on network are virtually absent, however according to openbenchmarking 50% performance at best is to be expected.
Announcement
Collapse
No announcement yet.
Anyone with HD5870 or HD5850 using recent opensource driver and kernel?
Collapse
X
-
Originally posted by bridgman View PostNecro-lover said that, not me. I said 4 regular ALUs (X, Y, Z, W) plus the specialized T unit.
Leave a comment:
-
Originally posted by crazycheese View PostBy the way, I have unrelated question about LLVM and GCC - does GCC folk have expressed the idea to fork current monolithic architecture and redesign a compiler using LLVM approach? Or are we fated to LLVM in the future when it comes to VLIW optimization?
Leave a comment:
-
Originally posted by crazycheese View PostCan you throw in compute comparsion between similar class chips (5870 vs 6950, for example)?
Because, according to bridgman, vliw4 has 4 full-featured units and vliw5 1 full, 4 simple ones.
Originally posted by crazycheese View PostAlso, do you know the state of opensource compute now?
Leave a comment:
-
Thanks, so I guess VLIW5 is not that bad if compiler gets to do its job..
AMD has jumped to nvidia-like scalar approach back with 7xxx. Why do single-chip GCN cards like 7970 have compute efficiency matching 6990?!
I thought the VLIW approach with the (precious) compiler eliminating any misses and optimizing loads is more efficient than scalar..? Any idea?
Originally posted by agd5f View PostWe've released detailed ISA documentation on all asics since r5xx including information on optimization. Additionally we provide a shader analyzer which is useful for optimizing shader code for AMD GPUs. Unfortunately, writing a good optimized compiler is a complex task regardless of how much documentation is available. Using a proper compiler framework is a good first step and Tom has already started working on support for AMD GPUs using LLVM. There are still being improvements made to the compilers for major CPU families (x86, ARM, etc.) and those are much more common than GPU instruction sets.
By the way, I have unrelated question about LLVM and GCC - does GCC folk have expressed the idea to fork current monolithic architecture and redesign a compiler using LLVM approach? Or are we fated to LLVM in the future when it comes to VLIW optimization?Last edited by crazycheese; 17 September 2012, 10:16 AM.
Leave a comment:
-
Originally posted by crazycheese View PostSo, the conclusion so far:
- VLIW5 is less efficient and more complex than VLIW4. Pre 6xxx are better recycled.
Originally posted by crazycheese View Post- The key why all Radeons (pre-Northern Island GPUs) are so slow with opensource driver - is absence of efficient compiler or whitepaper how to write it; which AMD is not releasing.
Leave a comment:
-
Originally posted by 0xBADCODE View Post...unless it comes to computations. You see, with proprietary catalyst driver VLIW5 beats VLIW4 on massively parallel computations. In fact it's quite hard to buy HD5xxx cards these days, even used ones. Most of medium and top range cards were bought by those who are doing high-performance computing for fun and profit.
So as for me it looks like compiler issue rather than anything else. In fact, VLIW4 seems to be lite version of VLIW5. AMD just saved some bucks on making smaller cheaper ICs and selling them as "new", "improved" thingies. Sure, they improved TDP. At cost of computations speed . Yet selling cards of same class under same price. Epic marketing win (for AMD).
source: https://en.bitcoin.it/wiki/Mining_hardware_comparison
5870 ->481
6970 ->433
But we talk about open source drivers right ? And its only true if the shader fit in the simple shader units.
Leave a comment:
-
Originally posted by crazycheese View Post- VLIW5 is less efficient and more complex than VLIW4. Pre 6xxx are better recycled.
Note that all of the NI parts except Cayman (HD69xx) are VLIW5, not VLIW4.
Originally posted by crazycheese View Post- The key why all Radeons (pre-Northern Island GPUs) are so slow with opensource driver - is absence of efficient compiler or whitepaper how to write it; which AMD is not releasing.
Originally posted by 0xBADCODE View Post...unless it comes to computations. You see, with proprietary catalyst driver VLIW5 beats VLIW4 on massively parallel computations. In fact it's quite hard to buy HD5xxx cards these days, even used ones. Most of medium and top range cards were bought by those who are doing high-performance computing for fun and profit.
For low end parts running mostly traditional graphics workloads, VLIW5 is still probably the most efficient.
Leave a comment:
-
Originally posted by 0xBADCODE View Post...unless it comes to computations. You see, with proprietary catalyst driver VLIW5 beats VLIW4 on massively parallel computations. In fact it's quite hard to buy HD5xxx cards these days, even used ones. Most of medium and top range cards were bought by those who are doing high-performance computing for fun and profit.
So as for me it looks like compiler issue rather than anything else. In fact, VLIW4 seems to be lite version of VLIW5. AMD just saved some bucks on making smaller cheaper ICs and selling them as "new", "improved" thingies. Sure, they improved TDP. At cost of computations speed . Yet selling cards of same class under same price. Epic marketing win (for AMD).
Because, according to bridgman, vliw4 has 4 full-featured units and vliw5 1 full, 4 simple ones.
Also, do you know the state of opensource compute now?
Leave a comment:
Leave a comment: