Where communities thrive


  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
People
Activity
  • Mar 10 11:22
    gitcoinbot commented #23
  • Mar 10 11:22
    gitcoinbot commented #23
  • Mar 10 11:22
    gitcoinbot commented #23
  • Mar 10 11:21
    gitcoinbot commented #23
  • Mar 10 11:17
    gitcoinbot commented #20
  • Mar 10 10:08
    gitcoinbot commented #2
  • Mar 10 10:08
    gitcoinbot commented #2
  • Feb 07 12:07

    avive on core

    minor grammer edit (compare)

  • Jan 24 12:29
    gitcoinbot commented #20
  • Jan 24 12:29
    gitcoinbot commented #20
  • Jan 24 12:05
    avive commented #20
  • Jan 22 14:45

    avive on master

    Time proof generation and verif… (compare)

  • Jan 22 13:59

    moshababo on master

    Prover-Verifier temp integratio… (compare)

  • Jan 22 11:48

    avive on master

    Updated benchmarks Merge branch 'master' of https:… (compare)

  • Jan 22 09:30
    gitcoinbot commented #23
  • Jan 22 09:30
    gitcoinbot commented #23
  • Jan 22 09:30
    gitcoinbot commented #23
  • Jan 22 09:30
    gitcoinbot commented #23
  • Jan 22 09:30
    gitcoinbot commented #23
  • Jan 21 07:51
    avive closed #23
Roger
@mortdeus
stupid gboard
if you extend the compiler you get a much cleaner implementation than the hac
hacky way youd have to do it otherwise. would this be considered a valid alternative solution?
@avive ?
facundomedica
@facundomedica
If you do it from C you have to use the Intel intrinsics, if you do it directly from ASM just the instructions
Roger
@mortdeus
i wasnt intending to use C.
my plan is to extend the compiler to compile the more optimal has me
hash code when applicable
Roger
@mortdeus
regardi
regarding the overhead concern, the best way to avoid that is to modify the compiler directly because there are certain compiler directives that you can use when compiling the runtime
also who
there are functions in the commit that return 0 which i presume means unimplemented? panic("unimplemented") is fara
Roger
@mortdeus
Better.
Aviv Eyal
@avive
Roger hi - did you take a look here? https://github.com/spacemeshos/sha256-simd
So the idea is to use cpuid() to obtain the runtime CPU capabilities (e.g. AVX2, SHA) and pick the best implementation of sha256 for the supported architecture. So, for example of the SHA intel extension is reported by the CPU then the code-base that uses these instructions will be used....
So I
The bounty is open until the 15th and you are welcome to join
The readme for the project I mentioned above explains what cpu caps are supported. With this bounty, we extended the lib to support the Intel SHA extensions which are only implemented on modern AMD zen-arch cpus....
so these are cpu caps based optimizations. Beyond that there are go-specific optimizations that @svenski123 did to improve the pref on any supported cpu arch...
Roger
@mortdeus
Right, i understand the cpuid at runtime approach. I just ha
i just know alot about Go's internal workings and how to implement this solution to get the best performance
as somebody mentioned earlier, this function is likely to be called in rapidly which generates way more garbage than one would initially expect
Roger
@mortdeus
Go assembler is not like other assembly languages where what you write is basically what you get back in machine code
go assembler is better thought of as a textual representation of the plan 9 compilers IR bitcode
Roger
@mortdeus
therefore everytime you call this hash function, you create a call into the runtime.
Roger
@mortdeus
so im just going to build this functionality into the compiler. that way we get the most efficient code.
youll see what i mean when i submit my PR
facundomedica
@facundomedica
That would be really cool to see, I'm looking forward to it!
Aviv Eyal
@avive
Cool - looking forward to see your contribution !
coderrick
@coderrick
Is there an AMD server to test our benchmarks on?
facundomedica
@facundomedica
Yeah, @avive has the keys to it
Aviv Eyal
@avive
Hi guys. For our kind of use cases, we are interested in sequential hashing of a small amount of data. Please look here: https://github.com/spacemeshos/sha256-simd/blob/8575aafc88c9020b9bb99e4b255fcc729593ffc4/sha256_test.go#L2272
small amount of data = 32 bytes.... (the output size of sha256)
The MHPs benchmarks we published here: https://github.com/spacemeshos/POET/blob/master/benchmarks.md
are computed from TestSequential() linked above....
Please send me a private message with request to access the AMD dev server and I will send you the access key and ssh instructions
Aviv Eyal
@avive
So we care about the perf of single sha256 execution for 32 bytes of input and not the streaming perf of sha256 working over large amount of data
Aviv Eyal
@avive
Hi all, we are extending the contest by 3 more days until Jan 18th to allow a developer working on the task to complete his entry.
Exciting to already see the nice performance improvements
Roger
@mortdeus
why is it important that the performance is fast if it's not in consideration of hashing large amounts of data?
Aviv Eyal
@avive
Roger - we need it for the Spacemesh proofs of space time protocol which involved generation of proofs of space and proofs of space-time. Please see https://spacemesh.io for more info
@facundomedica @svenski123 - thank you for your great submissions to the POET contest! As the original contest date was today and you were the first 2 who submitted improved code - we tipped each of you with 5ETH award per the contest terms.
We are giving few more days for a 3rd contestant to have a chance to submit an improvement before announcing 1st place contest winner
Roger
@mortdeus
So ive glanced over the white paper and have a somewhat vague understanding of how proof of spacetime works. here let me move this to lobby
Aviv Eyal
@avive
If you are here then it means you were interested in proofs of elapsed time at some point and we announce this first here for you! We are happy to announce our POET summer of rust coding contest! See: https://spacemesh.io/summer-of-rust-contest/ - Open if you are a US developer who is interested to work on the Spacemesh protocol full time
Aviv Eyal
@avive
Vlad Silviu Farcas
@uivlis
Hello Poet team! Very keen to start work on the coding contest. I'm Vlad, by the way. Just another bounty hunter.
Pawan Dhananjay
@pawanjay176
Hi..Is this competition open only for US developers?
Aviv Eyal
@avive
Pawan - yes
IT guy
@pistolla
US developers only????