- Bolt Graphics builds RISC-V-based GPU to challenge Nvidia
- Support for CUDA on RISC-V could reduce software barriers for alternative accelerators
- Zeus targets path tracing, HPC, and large memory workloads versus traditional shaders
Bolt Graphics is continuing its plan to challenge Nvidia and AMD by building a graphics processor around a RISC-V controlled architecture rather than a conventional GPU design.
The Sunnyvale, Calif.-based startup’s Zeus architecture is a complete overhaul of graphics, rendering, and high-performance computing workloads.
Instead of relying on traditional shader-heavy designs, Zeus combines fixed-function hardware for rasterization, ray tracing, and path tracing with an internal SIMD engine.
A standalone Linux system
Control and scheduling tasks are handled by a RISC-V processor that also functions as a general-purpose processor, allowing Zeus to operate as a standalone Linux system rather than relying entirely on a host processor.
We’ve written about Bolt and Zeus in 2025, and the company used CES 2026 to showcase its plans that look even more viable following Nvidia’s decision to bring CUDA support to RISC-V systems.
With CUDA no longer tied exclusively to x86 or Arm hosts, a RISC-V-based accelerator stack becomes more practical for developers already invested in Nvidia’s software ecosystem.
Zeus cards support Vulkan and DirectX 12, as well as engines such as Unreal and Unity, while also supporting common programming environments used in HPC, including Python, Fortran, and OSL compiled via LLVM.
The prototype expansion card uses a PCIe 5.0 x16 interface and pairs LPDDR5X graphics memory with DDR5 SODIMM slots for the RISC-V processor.
Depending on the configuration, the total memory capacity can reach 384 GB on a single card.
Bolt plans several Zeus variants, including the Zeus 1c26-032, Zeus 2c26-064, Zeus 2c26-128, and Zeus 4c26-256, covering single-chip PCIe cards and multi-chip 2U server designs with a combined memory capacity greater than 2TB.
Networking is provided via integrated 400Gbps and 800Gbps interfaces for rendering farms and clustered workloads. These interfaces are designed to allow direct GPU-to-GPU connections without separate network interface cards.
The card also includes BMC and IPMI hardware, features more commonly found in servers than in consumer graphics cards.
Power consumption is limited for its class, with the card relying on a single 8-pin PCIe connector rated at up to 225W, while high-end server configurations scale up to 500W.
Bolt has made some intriguing performance claims (pinch of salt), including path tracing throughput several times that of Nvidia’s RTX 5090 and extreme gains in FP64 simulation workloads.
These figures are naturally based on internal testing and simulations, with actual hardware validation still pending.
If CUDA on RISC-V gains traction, Bolt’s approach could face fewer software hurdles than similar efforts in the past.
This of course still leaves execution risk, but technical leadership suggests that Bolt bets on ecosystem changes rather than brute force scale alone.
Via TechPowerUp
Follow TechRadar on Google News And add us as your favorite source to get our news, reviews and expert opinions in your feeds. Make sure to click the Follow button!
And of course you can too follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp Also.
