8 × AMD Instinct MI355X

Tested system

Processor: AMD EPYC 9575F
Graphics: AMD Instinct MI355X
Accelerator count: 8
Nodes: 1

Recorded results

Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.

MLPerf Inference / dlrm-v3Offline · v6.1 · Samples/s

8 × AMD Instinct MI355X

16,363^* Samples/s

Accuracy target / result: DLRM_NE: 0.8678795984098008 DLRM_ACC: 0.6962884623080815 DLRM_AUC: 0.7861666437936649
Weight precision: fp16,bf16,fp8
Division: open
System type: datacenter
Availability: available
Cores per processor: 64 cores per socket, 128 total cores, 256 threads
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: PyTorch 2.10.0+rocm7.2.3.git1a270074, Triton 3.6.0, ROCm 7.2.3
Operating system: Ubuntu 24.04.3 LTS (Noble Numbat), kernel 6.8.0-134-generic

MLPerf Inference / dlrm-v3Server · v6.1 · Queries/s

8 × AMD Instinct MI355X

16,194.40^* Queries/s

Accuracy target / result: DLRM_NE: 0.8678772746839061 DLRM_ACC: 0.6962803331970739 DLRM_AUC: 0.7861629372250531
Weight precision: fp16,bf16,fp8
Division: open
System type: datacenter
Availability: available
Cores per processor: 64 cores per socket, 128 total cores, 256 threads
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: PyTorch 2.10.0+rocm7.2.3.git1a270074, Triton 3.6.0, ROCm 7.2.3
Operating system: Ubuntu 24.04.3 LTS (Noble Numbat), kernel 6.8.0-134-generic

Processing & platform

Processor: AMD EPYC 9575F
Graphics: AMD Instinct MI355X

Connectivity & software

Operating system: Ubuntu 24.04.3 LTS (Noble Numbat), kernel 6.8.0-134-generic

System configuration

Processors per node: 2
Accelerator count: 8
Nodes: 1
Software stack: PyTorch 2.10.0+rocm7.2.3.git1a270074, Triton 3.6.0, ROCm 7.2.3
Submission division: open

* Provisional data