building for digital abundance

Resources and Software

We offer a variety of resources and software to support your research and development needs. We also encourage inspecting our BSD 3-Clause and APL 2.0 compatible licenses.

Open Source Software

Vecmat

A simple-to-use, yet robust math and linear algebra library in C for 2d/3d graphics, machine learning, physics, and science — check GitHub and the latest docs.

CPU Feature Support

  • AVX supported
  • AVX2 (FMA3) supported
  • AVX-512F (AVX-512 FMA) supported
  • AVX10 (FMA3) work in progress
  • AVX10.1 (Xeon 6) coming in 2027
  • AVX10.2 (Xeon 7) tbd
  • SVE (ARMv8.2-A+) supported
  • SVE2 (ARMv9) supported

MMA Support

  • WMMA / MMA (NVIDIA/CUDA) work in progress
  • MFMA / WMMA (AMD/ROCm) work in progress
  • AMX (4th-7th generation Intel Xeon) coming in 2027
  • SME / SME2 (ARMv9.2-A+) tbd

Microserve

A modern HTTP server for experimentation and development supporting HTTP/3, HTTP/2, and HTTP/1.1.

Protocol Support

  • HTTP/3 (RFC9114) supported
    • QUIC: A UDP-Based Multiplexed and Secure Transport (RFC9000) supported
    • HTTP/3 Extended CONNECT (RFC9220) coming in 2027
  • HTTP/2 (RFC 9113) supported
  • HTTP/1.1 (RFC 9112) supported

NOTICE: Not all the projects are public, we are making preparations for public release. Unfortunately, the current environment of AI agents can just copy code and strip it of license, or illegally rewrite it is a major concern. We feel the current situation hinders technological development globally; nevertheless, we will make considerable efforts to public everything we can in a way that doesn't damage our business strategy and goals.

Open Source Licenses

Meanwhile, you can check out our open source licenses that will tackle in the future this probably exactly:

Vectorized Type Reference by Vendor

Intel (CPU)

Generation AVX Supported Types AMX Supported Types
4th Gen Xeon AVX, AVX2, AVX-512 AMX-TILE, AMX-BF16, AMX-INT8
5th Gen Xeon AVX, AVX2, AVX-512 AMX-TILE, AMX-BF16, AMX-INT8
Xeon 6 AVX, AVX2, AVX-512, AVX10.1 AMX-TILE, AMX-BF16, AMX-INT8, AMX-FP16
Xeon 7 AVX, AVX2, AVX-512, AVX10.1, AVX10.2 AMX-TILE, AMX-BF16, AMX-INT8, AMX-FP16, AMX-FP8, AMX-TF32, AMX-AVX512

AMD (CPU)

Generation Architecture Supported Vector Extensions
2nd/3rd Gen EPYC
(Rome/Milan)
Zen 2 / Zen 3 AVX, AVX2
4th Gen EPYC
(Genoa/Bergamo)
Zen 4 / Zen 4c AVX, AVX2, AVX-512
(256-bit data path)
5th Gen EPYC
(Turin)
Zen 5 / Zen 5c AVX, AVX2, AVX-512
(native 512-bit data path)

ARM (CPU)

Generation / Extension SVE Support Supported Types
ARMv8.2-A+ SVE (optional) Z0–Z31 (128–2048-bit);
P0–P15; INT8, INT16, INT32, INT64, FP16, FP32, FP64
ARMv9-A SVE2 (baseline) Z0–Z31 (128–2048-bit);
P0–P15; INT8, INT16, INT32, INT64, FP16, FP32, FP64
ARMv9.2+ SVE2 + SME/SME2 (optional) Z0–Z31, P0–P15, ZA tiles;
INT8, INT16, INT32, INT64, BF16, FP16, FP32, FP64

NVIDIA (GPU)

Generation Tensor Core Gen / API Supported Types (A/B → Acc)
Ampere (SM 8.0)
(A100)
3rd Gen
WMMA + mma.sync
FP16 → FP16 / FP32
BF16, TF32 → FP32
FP64 → FP64
INT8, INT4 → INT32
Ada Lovelace (SM 8.9)
(L40/L40S/L4)
4th Gen
WMMA + mma.sync
FP16 → FP16 / FP32
BF16, TF32 → FP32
FP64 → FP64
INT8, INT4 → INT32
FP8 → FP16 / FP32
Hopper (SM 9.0)
(H100/H200)
4th Gen
WMMA + mma + wgmma
FP16 → FP16 / FP32
BF16, TF32 → FP32
FP64 → FP64
INT8 → INT32
FP8 → FP16 / FP32
Blackwell (SM 10.x)
(B100/B200)
5th Gen
tcgen05.mma
FP16 → FP16 / FP32
BF16, TF32 → FP32
FP64 → FP64
INT8 → INT32
FP8 → FP16 / FP32
FP6, FP4, MXFP, NVFP4 → FP32

AMD (GPU)

Generation Architecture Supported Types (A/B → Acc)
MI100 series
(MI100)
CDNA1 FP32 → FP32
FP16, BF16 → FP32
INT8 → INT32
MI200 series
(MI210/MI250/MI250X)
CDNA2 FP32 → FP32
FP16, BF16 → FP32
INT8 → INT32
FP64 → FP64
MI300 series
(MI300A/X, MI325X)
CDNA3 FP32 → FP32
FP16, BF16, FP8, BF8, TF32 → FP32
INT8 → INT32
MI350 series
(MI350X/MI355X)
CDNA4 FP32 → FP32
FP16, BF16, FP8, BF8, FP6, FP4, TF32, MXFP → FP32
INT8 → INT32

Intel (GPU)

Generation Architecture / XMX Supported Types (A/B → Acc)
Alchemist
(Arc A-series A310/A380/A580, A750/A770)
Xe-HPG
XMX (DPAS)
FP16, BF16 → FP32
INT8, INT4, INT2 → INT32
Battlemage
(Arc B-series B570/B580)
Xe2-HPG
XMX (enhanced)
FP16, BF16, TF32 → FP32
INT8, INT4, INT2 → INT32