Torch Hammer benchmark report

Sirius — Sirius A100 1-GPU 8-benches stress — full_x3200c0s13b1n0_20261111_190621.json
source: full_x3200c0s13b1n0_20261111_190621.json GPU: NVIDIA A100-SXM4-40GB nodes: 1 GPUs: 1 benchmarks: 8
nodes
1
GPUs
1
benchmarks
8
outliers
0

(a) Batched GEMM (float32) [TFLOP/s]

fleet mean: 18.9 TFLOP/s | mean power: 316W | max temp: 47 C
Fleet distribution of GPU mean performance (TFLOP/s)
0 0 0 0 1 GPU count 18.9–19.9 TFLOP/s: 1 GPUs 19.4 TFLOP/s mean
Fleet distribution of GPU mean power (W)
0 0 1 GPU count 316–317 W: 1 GPUs 316 W mean
Fleet distribution of GPU max temperature (°C)
0 0 1 GPU count 47.0–48.0 °C: 1 GPUs 47.5 °C mean
Fleet distribution of GPU mean SM utilization (%)
0 0 1 GPU count 100–101 %: 1 GPUs 100 % mean
Fleet distribution of GPU mean memory BW utilization (%)
0 0 1 GPU count 19.2–20.2 %: 1 GPUs 19.7 % mean
Fleet distribution of GPU mean GPU clock (MHz)
0 0 1 GPU count 1,410–1,411 MHz: 1 GPUs 1,410 MHz mean
node GPU 0 node mean vs fleet thrt
x3200c0s13b1n01919+0.0%

(b) Convolution (float32) [img/s]

fleet mean: 9,369,501.7 img/s | mean power: 390W | max temp: 50 C
Fleet distribution of GPU mean performance (img/s)
0 0 0 0 1 GPU count 9.4M–9.4M img/s: 1 GPUs 9.4M img/s mean
Fleet distribution of GPU mean power (W)
0 0 1 GPU count 390–391 W: 1 GPUs 391 W mean
Fleet distribution of GPU max temperature (°C)
0 0 1 GPU count 50.0–51.0 °C: 1 GPUs 50.5 °C mean
Fleet distribution of GPU mean SM utilization (%)
0 0 1 GPU count 99.0–100 %: 1 GPUs 99.5 % mean
Fleet distribution of GPU mean memory BW utilization (%)
0 0 1 GPU count 72.1–73.1 %: 1 GPUs 72.6 % mean
Fleet distribution of GPU mean GPU clock (MHz)
0 0 1 GPU count 1,396–1,397 MHz: 1 GPUs 1,396 MHz mean
node GPU 0 node mean vs fleet thrt
x3200c0s13b1n09,369,5029,369,502+0.0%

(c) Einsum Attention (float32) [TFLOP/s]

fleet mean: 17.1 TFLOP/s | mean power: 346W | max temp: 52 C
Fleet distribution of GPU mean performance (TFLOP/s)
0 0 0 0 1 GPU count 17.1–18.1 TFLOP/s: 1 GPUs 17.6 TFLOP/s mean
Fleet distribution of GPU mean power (W)
0 0 1 GPU count 346–347 W: 1 GPUs 346 W mean
Fleet distribution of GPU max temperature (°C)
0 0 1 GPU count 52.0–53.0 °C: 1 GPUs 52.5 °C mean
Fleet distribution of GPU mean SM utilization (%)
0 0 1 GPU count 100–101 %: 1 GPUs 100 % mean
Fleet distribution of GPU mean memory BW utilization (%)
0 0 1 GPU count 26.1–27.1 %: 1 GPUs 26.6 % mean
Fleet distribution of GPU mean GPU clock (MHz)
0 0 1 GPU count 1,410–1,411 MHz: 1 GPUs 1,410 MHz mean
node GPU 0 node mean vs fleet thrt
x3200c0s13b1n01717+0.0%

(d) Memory Traffic (float32) [GB/s]

fleet mean: 29.6 GB/s | mean power: 194W | max temp: 51 C
Fleet distribution of GPU mean performance (GB/s)
0 0 0 0 1 GPU count 29.6–30.6 GB/s: 1 GPUs 30.1 GB/s mean
Fleet distribution of GPU mean power (W)
0 0 1 GPU count 194–195 W: 1 GPUs 194 W mean
Fleet distribution of GPU max temperature (°C)
0 0 1 GPU count 51.0–52.0 °C: 1 GPUs 51.5 °C mean
Fleet distribution of GPU mean SM utilization (%)
0 0 1 GPU count 100–101 %: 1 GPUs 100 % mean
Fleet distribution of GPU mean memory BW utilization (%)
0 0 1 GPU count 51.6–52.6 %: 1 GPUs 52.1 % mean
Fleet distribution of GPU mean GPU clock (MHz)
0 0 1 GPU count 1,410–1,411 MHz: 1 GPUs 1,410 MHz mean
node GPU 0 node mean vs fleet thrt
x3200c0s13b1n03030+0.0%

(e) Heat Equation (float32) [MLUPS]

fleet mean: 15,499.4 MLUPS | mean power: 289W | max temp: 44 C
Fleet distribution of GPU mean performance (MLUPS)
0 0 0 0 1 GPU count 15k–16k MLUPS: 1 GPUs 15k MLUPS mean
Fleet distribution of GPU mean power (W)
0 0 1 GPU count 289–290 W: 1 GPUs 290 W mean
Fleet distribution of GPU max temperature (°C)
0 0 1 GPU count 44.0–45.0 °C: 1 GPUs 44.5 °C mean
Fleet distribution of GPU mean SM utilization (%)
0 0 1 GPU count 99.4–100 %: 1 GPUs 99.9 % mean
Fleet distribution of GPU mean memory BW utilization (%)
0 0 1 GPU count 100–101 %: 1 GPUs 100 % mean
Fleet distribution of GPU mean GPU clock (MHz)
0 0 1 GPU count 1,410–1,411 MHz: 1 GPUs 1,410 MHz mean
node GPU 0 node mean vs fleet thrt
x3200c0s13b1n015,49915,499+0.0%

(f) Schrödinger Equation (float32) [iter/s]

fleet mean: 58.8 iter/s | mean power: 201W | max temp: 44 C
Fleet distribution of GPU mean performance (iter/s)
0 0 0 0 1 GPU count 58.8–59.8 iter/s: 1 GPUs 59.3 iter/s mean
Fleet distribution of GPU mean power (W)
0 0 1 GPU count 201–202 W: 1 GPUs 202 W mean
Fleet distribution of GPU max temperature (°C)
0 0 1 GPU count 44.0–45.0 °C: 1 GPUs 44.5 °C mean
Fleet distribution of GPU mean SM utilization (%)
0 0 1 GPU count 99.2–100 %: 1 GPUs 99.7 % mean
Fleet distribution of GPU mean memory BW utilization (%)
0 0 1 GPU count 100–101 %: 1 GPUs 100 % mean
Fleet distribution of GPU mean GPU clock (MHz)
0 0 1 GPU count 1,410–1,411 MHz: 1 GPUs 1,410 MHz mean
node GPU 0 node mean vs fleet thrt
x3200c0s13b1n05959+0.0%

(g) Atomic Contention (float32) [Gops/s]

fleet mean: 9.2 Gops/s | mean power: 124W | max temp: 41 C
Fleet distribution of GPU mean performance (Gops/s)
0 0 0 0 1 GPU count 9.2–10.2 Gops/s: 1 GPUs 9.7 Gops/s mean
Fleet distribution of GPU mean power (W)
0 0 1 GPU count 124–125 W: 1 GPUs 124 W mean
Fleet distribution of GPU max temperature (°C)
0 0 1 GPU count 41.0–42.0 °C: 1 GPUs 41.5 °C mean
Fleet distribution of GPU mean SM utilization (%)
0 0 1 GPU count 99.0–100 %: 1 GPUs 99.5 % mean
Fleet distribution of GPU mean memory BW utilization (%)
0 0 1 GPU count 9.0–10.0 %: 1 GPUs 9.5 % mean
Fleet distribution of GPU mean GPU clock (MHz)
0 0 1 GPU count 1,410–1,411 MHz: 1 GPUs 1,410 MHz mean
node GPU 0 node mean vs fleet thrt
x3200c0s13b1n099+0.0%

(h) Sparse MM (float32) [GFLOP/s]

fleet mean: 242.7 GFLOP/s | mean power: 220W | max temp: 43 C
Fleet distribution of GPU mean performance (GFLOP/s)
0 0 0 0 1 GPU count 243–244 GFLOP/s: 1 GPUs 243 GFLOP/s mean
Fleet distribution of GPU mean power (W)
0 0 1 GPU count 220–221 W: 1 GPUs 221 W mean
Fleet distribution of GPU max temperature (°C)
0 0 1 GPU count 43.0–44.0 °C: 1 GPUs 43.5 °C mean
Fleet distribution of GPU mean SM utilization (%)
0 0 1 GPU count 100–101 %: 1 GPUs 100 % mean
Fleet distribution of GPU mean memory BW utilization (%)
0 0 1 GPU count 5.5–6.5 %: 1 GPUs 6.0 % mean
Fleet distribution of GPU mean GPU clock (MHz)
0 0 1 GPU count 1,410–1,411 MHz: 1 GPUs 1,410 MHz mean
node GPU 0 node mean vs fleet thrt
x3200c0s13b1n0243243+0.0%

Outliers

None detected