Technology
What's built, what's verified, what's next.
Two chips in the open: the GRX930 RISC-V SoC with dual NPUs, and the G100 GPU. A photonic tensor accelerator
is in design, and GRXCP ties them together with a CUDA-style programming model. Every row below says how far it has been proven.
GRIDWORKZ PLATFORM
Select a block to view its source, docs and status →
Specifications
Specs matrix
Verified in simTiming closedIn progressDesign
| Block | Parameter | Specification | Status |
|---|---|---|---|
| GRX930 | CPU | 4 × RV64IMAC, 5-stage in-order, AMO/LR/SC | Verified in sim |
| GRX930 | Caches | Per-core I/D caches (256-bit lines); shared 4-way write-back L2 with invalidation coherence | Verified in sim |
| GRX930 | NPU | 2 × 8×8 systolic GEMM, DMA, command queue (depth 4), sigmoid/tanh activation | Verified in sim |
| GRX930 | NPU datatypes | INT4, INT8, INT16, FP16, BF16 (18/18 sweep cases pass) | Verified in sim |
| GRX930 | Fabric | 4-master AXI4 crossbar, 64-bit data; DMA arbiter with equivalence gate | Verified in sim |
| GRX930 | FPGA | Artix-7 xc7a200t (Nexys Video): ~121 MHz post-implementation, 0 failing endpoints | Timing closed |
| GRX930 | FPGA utilization | 125,735 LUTs (94%), 67,007 FFs, 55 BRAM, 227 DSP | Timing closed |
| GRX930 test chip | Process | GF180MCU 180 nm via wafer.space: single core, 50 MHz, boots from on-chip ROM. GDS due Dec 16, 2026 | In progress |
| G100 | Architecture | Vortex-based RISC-V GPU: tensor cores (WGMMA), DXA, ray tracing, graphics pipeline | Verified in sim |
| G100 | Tensor formats | fp32, tf32, fp16, bf16, fp8, bf8, int8 | Verified in sim |
| G100 | Discovery config | 1 cluster × 4 cores, TCU + DXA; SGEMM K=64/512 pass vs host reference, pending independent review | In progress |
| PTA | Photonic tile | 128 × 64 GEMM tile, planned as a chiplet beside the G100; error-modelled against a frozen MNIST canary | Design |
| Software | GRXCP | CUDA-style runtime (libgrxrt), single-source compiler (grxcc), grxBLAS, grx-smi / grx-prof / grx-sanitize | In progress |
| Verification | Tools | Icarus Verilog, SymbiYosys formal, Verilator; G100 on SimX and RTL simulation | Verified in sim |
No matching specs.
Software
GRXCP: the GRX Compute Platform.
A CUDA-class programming platform for the G100 and GRX930. Write __global__ kernels and <<<grid, block>>> launches in one file; grxcc splits and compiles it, and libgrxrt runs it on top of the G100 driver.
- libgrxrt runtime: grxMalloc, grxMemcpy, streams, events
- grxcc single-source compiler driver, built on the VOLT LLVM toolchain
- grxBLAS and friends, including an int8 GEMM route for the PTA
- grx_cuda_compat.h maps cudaX to grxX, so porting CUDA is one include
In active development and tested on the G100 simulators.
// From grxcp/tests/grxcc/vecadd.grx.cpp
#include <grx/grx.h>
__global__ void axpy(const float* x, float* y,
unsigned int n, float a) {
const unsigned int i = blockIdx.x * blockDim.x + threadIdx.x;
if (i < n) y[i] = a * x[i] + y[i];
}
// Host side, same file
grxMalloc((void**)&dx, n * sizeof(float));
grxMalloc((void**)&dy, n * sizeof(float));
axpy<<<grid, block>>>(dx, dy, n, alpha);
grxDeviceSynchronize();
grxMemcpy(got.data(), dy, n * sizeof(float), grxMemcpyDefault);