Performance data for WASM SIMD instructions.

Last update: Jul 24, 2022

Related tags

Overview

WASM SIMD Data

This repository contains code and data which can be used to generate a JSON file containing information about the WASM SIMD proposal. For an example of the output, see this gist. Note that the current output contains many more instructions.

The data/ directory contains descriptions of the API, including opcodes, instruction names and parameters, as well as data about the corresponding higher-level APIs in both wasm_simd128.h and WAV.

The lowering/ directory then uses that information to generate more data on which instructions are expected to be used on various architectures to implement the WASM SIMD instructions, as well as performance data (number of uOps and latency). Note that this data should not currently be considered accurate; the lowering/ directory has more information, but basically many of the functions have not yet been optimized and engines such as V8 are likely to contain much better implementations.

For information on how to generate the lowering data, please see the README in the lowering/ directory.

Once you have generated the lowering data, you can generate the final output using scripts/generate.py. If you provide an argument to that scrip it will be used as an output file for a minified (no extra whitespace) JSON dump. If you do not provide an argument a non-minified JSON dump of the same data intended to be (relatively speaking) human-readable will be sent to stdout.

Please note that the format of this data should not be considered stable (yet?).

License

The license for the data has not yet been determined. Currently, copy some information from the WebAssembly 128-bit packed SIMD Extension proposal, which means it would be subject to the W3C license, but I'm leaning towards re-writing those sections anyways. Not only would this allow us to use a more permissive license (perhaps even a public domain dedication), it would allow more flexibility in how the content is organized.

To generate the lowering data, the lowering/generate-makefile.py script is first used to generate a Makefile which contains rules to allow generating the rest of the lowering data in parallel. To use it, just redirect the output to Makefile; for example, ./generate-makefile.py > Makefile.

A Pythonic Data Catalog powered by Ray that brings exabyte-level scalability and fast, ACID-compliant, change-data-capture to your big data workloads.

DeltaCAT DeltaCAT is a Pythonic Data Catalog powered by Ray. Its data storage model allows you to define and manage fast, scalable, ACID-compliant dat

45 Oct 15, 2022

Viewflow is an Airflow-based framework that allows data scientists to create data models without writing Airflow code.

Viewflow Viewflow is a framework built on the top of Airflow that enables data scientists to create materialized views. It allows data scientists to f

114 Oct 12, 2022

resultados (data) de elecciones 2021 y código para extraer data de la ONPE

elecciones-peru-2021-ONPE Resultados (data) de elecciones 2021 y código para extraer data de la ONPE Data Licencia liberal, pero si vas a usarlo por f

21 Jun 14, 2021

The purpose of this code base is to add a specified signal-to-noise ratio noise from MUSAN dataset to a pure speech signal and to generate far-field speech data using room impulse response data from BUT Speech@FIT Reverb Database.

Add_noise_and_rir_to_speech The purpose of this code base is to add a specified signal-to-noise ratio noise from MUSAN dataset to a pure speech signal

7 Oct 30, 2022

An unofficial python API for trading on the DeGiro platform, with the ability to get real time data and historical data.

DegiroAPI An unofficial API for the trading platform Degiro written in Python with the ability to get real time data and historical data for products.

5 Dec 16, 2022

Improve current data preprocessing for FTM's WOB data to analyze Shell and Dutch Governmental contacts.

We're the hackathon leftovers, but we are Too Good To Go ;-). A repo by Lukas Schubotz and Raymon van Dinter. We aim to improve current data preprocessing for FTM's WOB data to analyze Shell and Dutch Governmental contacts.

5 Dec 9, 2021

Python for downloading model data (HRRR, RAP, GFS, NBM, etc.) from NOMADS, NOAA's Big Data Program partners (Amazon, Google, Microsoft), and the University of Utah Pando Archive System.

194 Jan 2, 2023

A program made in PYTHON🐍 that automatically performs data insertions into a POSTGRES database 🐘 , using as base a .CSV file 📁 , useful in mass data insertions

A program made in PYTHON🐍 that automatically performs data insertions into a POSTGRES database 🐘 , using as base a .CSV file 📁 , useful in mass data insertions.

1 Oct 17, 2022

Explore-bikeshare-data - GitHub project as part of the Programming for Data Science with Python Nanodegree from Udacity

Date created February 10, 2022 Project Title Explore US Bikeshare Data Descripti

1 Feb 14, 2022

Comments

Different instructions may be generated for different immediates

For instructions with immediate-mode parameters, the compiler may generate different instruction(s). For example,

#include <stdint.h>

typedef int32_t i32x4 __attribute__((__vector_size__(16)));

i32x4
replace_lane_0(i32x4 v, int32_t value) {
    v[0] = value;
    return v;
}

i32x4
replace_lane_1(i32x4 v, int32_t value) {
    v[1] = value;
    return v;
}

Compiler Explorer: https://godbolt.org/z/9beqbP4Wj

Generates:

replace_lane_0(int __vector(4), int):               # @replace_lane_0(int __vector(4), int)
        movd    xmm1, edi
        movss   xmm0, xmm1                      # xmm0 = xmm1[0],xmm0[1,2,3]
        ret
replace_lane_1(int __vector(4), int):               # @replace_lane_1(int __vector(4), int)
        movd    xmm1, edi
        punpcklqdq      xmm1, xmm0              # xmm1 = xmm1[0],xmm0[0]
        shufps  xmm1, xmm0, 226                 # xmm1 = xmm1[2,0],xmm0[2,3]
        movaps  xmm0, xmm1
        ret

I haven't worked out all the details yet, but for most instructions I think it will be possible to work around this by generating all possible values; with the exception of shuffle, worst case is only 16. We'll have to do some work parsing the assembly to deduplicate the results, but nothing too complex.

Shuffle is obviously the exception here, but that's nothing new. For that, I think the best option is just to link to Compiler Explorer and let people plug in their own values.

opened by nemequ 1

Add initial mechanism for capturing Firefox lowerings

@nemequ, this PR actually has a few different parts and I do not mind splitting it up if you prefer. It adds C files for every Wasm SIMD instruction, converts those to WAT (using a recent version of clang), uses the SpiderMonkey shell to retrieve the lowerings, and disassembles these using capstone's Python interface. Let me know what you think!

I don't exactly know how to integrate this with, e.g., your deploy/wasm-simd-data.json file, but this seemed like enough change for now.

opened by abrown 0

Owner

Evan Nemerson

GitHub

peace-performance (Rust) binding for python. To calculate star ratings and performance points for all osu! gamemodes

peace-performance-python Fast, To calculate star ratings and performance points for all osu! gamemodes peace-performance (Rust) binding for python bas

9 Sep 19, 2022

DownTime-Score is a Small project aimed to Monitor the performance and the availabillity of a variety of the Vital and Critical Moroccan Web Portals

DownTime-Score DownTime-Score is a Small project aimed to Monitor the performance and the availabillity of a variety of the Vital and Critical Morocca

5 Apr 30, 2022

This is an online course where you can learn and master the skill of low-level performance analysis and tuning.

Performance Ninja Class This is an online course where you can learn to find and fix low-level performance issues, for example CPU cache misses and br

1.2k Dec 30, 2022

EasyBuild is a software build and installation framework that allows you to manage (scientific) software on High Performance Computing (HPC) systems in an efficient way.

87 Dec 27, 2022

Developed a website to analyze and generate report of students based on the curriculum that represents student’s academic performance.

Developed a website to analyze and generate report of students based on the curriculum that represents student’s academic performance. We have developed the system such that, it will automatically parse data onto the database from excel file, which will in return reduce time consumption of analysis of data.

3 Nov 8, 2022