Hardware caveat#
Every card records the device it was measured on: its name, compute capability or CPU model, and, for a GPU, the FP64 throughput and memory bandwidth the card’s ratios are taken against. The devices with a committed card are listed below; the lists are generated from the cards, so a device added next to them appears here without an edit.
GPUs#
device |
compute capability / CPU model |
date |
|---|---|---|
NVIDIA H100 80GB HBM3 |
9.0 |
2026-10-13 |
NVIDIA L4 |
8.9 |
2026-10-14 |
NVIDIA A100-SXM4-40GB |
8.0 |
2026-10-13 |
Tesla T4 |
7.5 |
2026-10-13 |
Quadro P2000 |
6.1 |
2026-10-13 |
NVIDIA RTX PRO 6000 Blackwell Server Edition |
12.0 |
2026-10-14 |
device |
driver |
CUDA runtime |
host CPU |
Warp |
JAX |
PyTorch |
CuPy |
|---|---|---|---|---|---|---|---|
NVIDIA H100 80GB HBM3 |
580.178.04 |
12.9 |
Intel Xeon Platinum 8481C CPU @ 2.70GHz |
1.17.0 |
0.11.2 |
2.12.1+cu129 |
14.2.0 |
NVIDIA L4 |
580.178.04 |
12.9 |
Intel Xeon CPU @ 2.20GHz |
1.17.0 |
0.11.2 |
2.12.1+cu129 |
14.2.0 |
NVIDIA A100-SXM4-40GB |
580.178.04 |
12.9 |
Intel Xeon CPU @ 2.20GHz |
1.17.0 |
0.11.2 |
2.12.1+cu129 |
14.2.0 |
Tesla T4 |
580.178.04 |
12.9 |
Intel Xeon CPU @ 2.00GHz |
1.17.0 |
0.11.2 |
2.12.1+cu129 |
14.2.0 |
Quadro P2000 |
560.35.03 |
12.9 |
Intel Xeon W-2125 CPU @ 4.00GHz |
1.17.0 |
0.11.2 |
2.12.1 |
14.2.0 |
NVIDIA RTX PRO 6000 Blackwell Server Edition |
580.178.04 |
12.9 |
AMD EPYC 9B45 |
1.17.0 |
0.11.2 |
2.12.1+cu129 |
14.2.0 |
CPUs#
device |
compute capability / CPU model |
date |
|---|---|---|
AMD EPYC 9B45 |
AMD EPYC 9B45 |
2026-10-13 |
AMD EPYC 7B13 |
AMD EPYC 7B13 |
2026-10-13 |
Google Axion (Arm Neoverse-V2) |
aarch64 |
2026-10-13 |
Intel Xeon Platinum 8581C |
INTEL(R) XEON(R) PLATINUM 8581C CPU @ 2.30GHz |
2026-10-13 |
device |
driver |
CUDA runtime |
host CPU |
Warp |
JAX |
PyTorch |
CuPy |
|---|---|---|---|---|---|---|---|
AMD EPYC 9B45 |
– |
– |
AMD EPYC 9B45 |
– |
– |
– |
– |
AMD EPYC 7B13 |
– |
– |
AMD EPYC 7B13 |
– |
– |
– |
– |
Google Axion (Arm Neoverse-V2) |
– |
– |
aarch64 |
– |
– |
– |
– |
Intel Xeon Platinum 8581C |
– |
– |
INTEL XEON PLATINUM 8581C CPU @ 2.30GHz |
– |
– |
– |
– |
The method transfers to other hardware unchanged; the absolute numbers, and the crossover points between arms, differ from device to device, because FP64 throughput, memory bandwidth, launch overhead and core counts differ. Reading the numbers describes the NVIDIA H100 card and the AMD EPYC 9B45 card and names the device wherever it quotes another; each other device has its own tab on the results pages. A card from a new device is added beside these, produced by the same scripts.
One device is worth a note. The Tesla T4 (Kaggle, power-capped at 70 W) showed significant SM clock fluctuations between and within arm blocks, so its cells can move more from run to run; each card records the SM clock of every timed run.