PantheonSim / GPUs / NVIDIA B200

Simulated NVIDIA B200: a GPU profile for CUDA and ROCm testing

PantheonSim, the GPU simulator for CUDA and ROCm, simulates the NVIDIA B200 (Blackwell, 10.0) as the profile nvidia/b200. NVIDIA's Blackwell data-center GPU for AI training and inference, with HBM3e memory and NVLink 5. Its profile is built from public documents and not yet measured against a physical card.

The profile at a glance

These are the numbers a program can ask this simulated GPU, and the values nvidia-smi show for it. They come from the profile file in the simulator's repository, pinned to one commit of it.

Property	Value
Profile id	`nvidia/b200`
Vendor and architecture	NVIDIA, Blackwell
Compute capability	`10.0`
Device memory	179.1 GiB, HBM
Streaming multiprocessors	148
Warp size	32
Max threads per multiprocessor	2048
Shared memory per block (opt-in maximum)	227 KiB
Memory bus width	8192-bit
Power limit (profile)	1000 W
Maximum clocks (profile)	1965 MHz shader, 4000 MHz memory
ECC memory	yes
PCIe link reported	Gen5 x16
NVLink reported	NVLink5 x18
Tensor or matrix cores	yes
Verified (measured on a physical card)	not yet measured

What this GPU is for

NVIDIA's Blackwell data-center GPU for AI training and inference, with HBM3e memory and NVLink 5.

Blackwell is split across several compute capabilities in these profiles: 10.0 for the B200 and GB200, 10.3 for the B300, 11.0 for Jetson Thor, 12.0 for the GeForce RTX 50 series and the RTX PRO 6000 cards, and 12.1 for the GB10. Only the RTX PRO 6000 Server Edition was read from a physical card.

Among the 37 NVIDIA profiles it ranks 4th by device memory (179.1 GiB) and 6th by SMs (148), counting the largest as first.

Is this profile verified?

No. This profile is marked not verified: it is built from public documents only, and nothing in it was measured on a physical card. Some figures are derived or copied from the nearest profile where the vendor publishes none, so treat them as approximate, and memory sizes as upper bounds. The profile file itself calls some of its values placeholders. Programs still run on it, and it still answers every call as the architecture's rules require, but a value such as a clock or a limit may differ from a real card's.

Simulate this GPU

Build the simulator (see the docs) or open the playground, then:

nvcc -cudart shared -arch=compute_100 my_app.cu -o my_app
vgpu run --gpu nvidia/b200 ./my_app
vgpu shell -y --gpu nvidia/b200 --count 4
vgpu info --gpu nvidia/b200

This profile is compute capability 10.0. A kernel built for compute_75 runs on it and on every other NVIDIA profile; a kernel built for a newer architecture is refused by a profile that is older than it. Blackwell targets need CUDA 12.8 or newer. Link the CUDA runtime shared (-cudart shared) so the simulator can stand in for it.

To use it every time, put gpu: nvidia/b200 in a pantheonsim.yaml settings file, or in a GitHub Actions job give the PantheonSim action gpu: nvidia/b200 (see CUDA and HIP tests in GitHub Actions). The simulator checks behaviour and has no timing model, so a run on a physical GPU before a release still counts. The CUDA guide explains the rest.

Where the numbers come from

Each profile file begins with a note on its sources. This is the note for NVIDIA B200, as written in the file:

Source note for nvidia/b200

Public documentation values (sm_100). Blackwell public data is thinner than Hopper's; several values here are best-effort placeholders and MUST be revisited by hardware characterization. verified: false.

The GPU index lists every profile, and this one is not yet measured.

Other Blackwell profiles: