ewasm/Lobby

Hangout for eWASM discussion

cdetrio

@cdetrio

wasm-compilers-vs-interp-with-bignums-websnark-bn128pairings.png

Greg Colvin

@gcolvin

Thanks Casey.

chriseth

@chriseth

Is there any work being done on verifying an upper bound for the compiled code?

cdetrio

@cdetrio

upper bound on runtime? like "symbolic metering"?

Mamy Ratsimbazafy

@mratsim

FYI, WASM SIMD meeting, not sure of the date yet: WebAssembly/simd#150

mishaaaa

@mishaaaa

Hi, I was trying out the project (https://medium.com/wasm/compile-and-deploy-an-erc20-contract-on-ewasm-d91d890665e6). I failed to connect to ewasm test network from metamask. It tries to connect for some time and shows that it cannot be connected.

mishaaaa

@mishaaaa

Can someone help me point out the error also please let me know whether the public testnet URL http://ewasm.ethereum.org:8545 is up and running. Thanks in advance.

Achala Bhatt

@AchalaSB

Hey, have few questions on Gas metering. (referred https://ewasm.readthedocs.io/en/mkdocs/determining_wasm_gas_costs/)

Cycles are calculated based on bare metal CPU cycle or it is calculated based on wasm virtual machine cycle?
How the cycles are calculated ?

Hugo

@hugo-dc

@mishaaaa you can try running a local geth node, using this: https://github.com/jwasinger/ewasm-dev-env , after that you can connect Metamask to the local node: http://localhost:8545.

cdetrio

@cdetrio

@AchalaSB I believe those cycle numbers are taken from a book, in the references (the Agner Fog book?)

right now the gas cost table is a best guess. It needs to be evaluated by benchmarking, to see how accurately those gas costs can predict runtime in various engines. that's one of our current projects

mishaaaa

@mishaaaa

@hugo-dc Thanks for the reply. I was able to run a local node following the given link. But while deploying a contract the metamask shows that the account have insufficient funds. Can you let me know how can I get some ether for that account. Thanks in advance.

Hugo

@hugo-dc

@mishaaaa you can import the premined account in Metamask using this pk: https://github.com/jwasinger/ewasm-dev-env/blob/master/geth/keys/prefunded/prefunded-priv.txt

Achala Bhatt

@AchalaSB

@cdetrio can you share me link of the book.

cdetrio

@cdetrio

@AchalaSB it's in the page you linked, the References section.

Instruction tables by Agner Fog: http://www.agner.org/optimize/instruction_tables.pdf

Achala Bhatt

@AchalaSB

In the eWASM readme books it is mentioned that

Assumption 2: 1 second of CPU execution equals to 10 million gas (i.e. 1 gas equals to 0.1 us).

On what basis this assumptions are made?
And how the cycles are mentioned? Checked in book http://www.agner.org/optimize/instruction_tables.pdf in Haswell section couldn't able see those cycles for those operation

Achala Bhatt

@AchalaSB

How come it is 80 cycles for DIV opcode?

Paweł Bylica

@chfast

@AchalaSB It is just so slow.

Achala Bhatt

@AchalaSB

@chfast I know DIV operation is complex. but is the 80 cycles is an estimated number?
Or Is the cycle is exactly 80?

In Haswell table for DIV r32- it is mentioned the latency range 22-29
and for DIV r64- it is mentioned the latency range 32-96

But in gas-cost table for both i32 and i64 type it is mentioned 80 cycle

Mamy Ratsimbazafy

@mratsim

MOD and DIV are at least 55 cycles

I have a small bench to measure it here, should be easily ported to C/C++: https://github.com/status-im/nim-beacon-chain/blob/nbench/nbench/platforms/x86.nim#L100-L122

just make sure to use volatile load/store

Alex Beregszaszi

@axic

Oh nice!

@AchalaSB the 80 came from the haswell specs and not third party sources (it should be linked in the markdown)

cdetrio

@cdetrio

@AchalaSB here's a place where it says 80 for DIV:

Screen Shot 2019-12-19 at 10.59.27 AM.png

https://www.intel.com/content/dam/www/public/us/en/documents/manuals/64-ia-32-architectures-optimization-manual.pdf

oops I meant this one

Screen Shot 2019-12-19 at 11.01.16 AM.png

Paweł Bylica

@chfast

We still should be taking the upper bound (95) in this case.

Alex Beregszaszi

@axic

There was a different kind of spec with a fixed 80 cycle count, but can’t seem to find it. It wasn’t a spreadsheet.

Greg Colvin

@gcolvin

I wish we had some notion of how far off we can be and not get DoSed. If the code is interpreted these numbers will get drowned to some extent by the interpreter overhead, and if it is compiled the compiler itself and the tricks CPUs play will make cycle-counting only a guess. And the counting itself can be a significant overhead that will depend on how smart the injection is and how well the compiler can optimize it.

Achala Bhatt

@AchalaSB

Thanks
@axic can you share the document/spreadsheet you are referring to?

@jakelang you might know the reference book for CPU cycle, as you have commited for eWASM gas cost table.
https://github.com/ewasm/design/blob/mkdocs/docs/determining_wasm_gas_costs.md

Alex Beregszaszi

@axic

This is the original source of the document: https://gist.github.com/axic/5bf506728005864461454dd4d37a7f37

And it refers to “Appendix C” of https://software.intel.com/sites/default/files/managed/9e/bc/64-ia-32-architectures-optimization-manual.pdf of which @cetrio copy pasted.

Anyway, I wrote it over 3 years so don’t remember where the 80 came from.

Alex Beregszaszi

@axic

It likely seems to be a simplification of that spreadsheet.

mishaaaa

@mishaaaa

Hi all, Is it possible to write smart contracts in any language (like c,c++,rust,assemblyscrip)t using webassembly concept in ewasm. If yes it would be great if someone can share some links which can be used to do a quick POC on the same. Thanks in advance. :)

Jacques Wagener

@jacqueswww

https://github.com/status-im/nimplay

And search for wrc20 for more examples

https://gist.github.com/axic/16158c5c88fbc7b1d09dfa8c658bc363

Achala Bhatt

@AchalaSB

Hi, what is cost consumed for const in ewasm?
(or ex: if there is any equation like 1 + ( x/100) ) What is the cost for 1 and 100 ?

And what is the cost for keccak256 ?

Ajoy Das

@ajoydas

Where can I find Hera benchmarking results or is there any way to run evmone benchmark tests with Hera?

Paweł Bylica

@chfast

@ajoydas Hera wraps 3 different wasm engines. These engines and others were benchmarked by @cdetrio and others. I would need to dig up some slides presenting results. But running evmone benchmark suite in Hera is not directly possible, because these are EVM bytecodes, not wasm.

For EVM benchmarking results see https://github.com/ewasm/benchmarking/.

Ajoy Das

@ajoydas

@chfast thanks for the reply. It would be helpful if you can share the slides.
So, if we need to compare the performances between ewasm and evm, what is the correct way?
Will compiling benchmarking solidity contracts both in ewasm byte code and evm byte code and then taking the performance statistics be a proper way?

Where communities thrive

People

Repo info

Activity