GeekRadar / The comparison desk

COMPARE.

GPU

Nvidia

A100-PCIE-40GB

Graphics processor

Video memory: 40 GB^*
Memory bus: 5,120 bit^*
Rated memory bandwidth: 1,555 GB/s^*

Benchmark results

Geekbench GPU (reported compilation) · version unreported · CUDA215,434^*Platform unreported Compare results
Geekbench GPU (reported compilation) · version unreported · CUDA215,434^*Platform unreported Compare results
Geekbench GPU (reported compilation) · version unreported · OpenCL161,590^*Platform unreported Compare results
Geekbench GPU (reported compilation) · version unreported · OpenCL161,590^*Platform unreported Compare results
Geekbench GPU (reported compilation) · version unreported · Vulkan92,245^*Platform unreported Compare results
Geekbench GPU (reported compilation) · version unreported · Vulkan92,245^*Platform unreported Compare results

Processing & platform

Architecture: Ampere^*

Memory & storage

Video memory: 40 GB^*
Video memory type: HBM2^*
Memory bus: 5,120 bit^*
Rated memory bandwidth: 1,555 GB/s^*

System configuration

Detailed specifications

Specifications 1 · 20 fields

GPU architecture — NVIDIA A100 40GB PCIe — 40 GB HBM2: Ampere^*
Theoretical peak: BF16 tensor dense per GPU — NVIDIA A100 40GB PCIe — 40 GB HBM2: 312^* TFLOPS
Theoretical peak: FP16 tensor dense per GPU — NVIDIA A100 40GB PCIe — 40 GB HBM2: 312^* TFLOPS
Theoretical peak: FP32 non-tensor dense per GPU — NVIDIA A100 40GB PCIe — 40 GB HBM2: 19.5^* TFLOPS
Native hardware support: FP4 tensor — NVIDIA A100 40GB PCIe — 40 GB HBM2: No^*
Theoretical peak: FP64 non-tensor dense per GPU — NVIDIA A100 40GB PCIe — 40 GB HBM2: 9.7^* TFLOPS
Theoretical peak: FP64 tensor dense per GPU — NVIDIA A100 40GB PCIe — 40 GB HBM2: 19.5^* TFLOPS
Native hardware support: FP6 tensor — NVIDIA A100 40GB PCIe — 40 GB HBM2: No^*
Native hardware support: FP8 tensor — NVIDIA A100 40GB PCIe — 40 GB HBM2: No^*
Theoretical peak: INT8 tensor dense per GPU — NVIDIA A100 40GB PCIe — 40 GB HBM2: 624^* TOPS
Theoretical peak: TF32 tensor dense per GPU — NVIDIA A100 40GB PCIe — 40 GB HBM2: 156^* TFLOPS
Physical configuration — NVIDIA A100 40GB PCIe — 40 GB HBM2: PCIe, dual-slot FHFL^*
GPU interconnect bandwidth (NVLink 3) — NVIDIA A100 40GB PCIe — 40 GB HBM2: 600^* GB/s
PCIe interface declaration — NVIDIA A100 40GB PCIe — 40 GB HBM2: PCIe Gen4 x16^*
Maximum board power — NVIDIA A100 40GB PCIe — 40 GB HBM2: 250^* W
Peak memory bandwidth per GPU — NVIDIA A100 40GB PCIe — 40 GB HBM2: 1,555^* GB/s
Memory interface width per GPU — NVIDIA A100 40GB PCIe — 40 GB HBM2: 5,120^* bit
Memory capacity per GPU — NVIDIA A100 40GB PCIe — 40 GB HBM2: 40^* GB
Memory technology — NVIDIA A100 40GB PCIe — 40 GB HBM2: HBM2^*
GPU model — NVIDIA A100 40GB PCIe — 40 GB HBM2: NVIDIA A100 40GB PCIe^*

Specifications 2 · 5 fields

Manufacturer

Nvidia^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

Device

A100-PCIE-40GB^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

CUDA

215,434^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

OpenCL

161,590^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

Vulkan

92,245^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

Specifications 3 · 5 fields

Manufacturer

Nvidia^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

Device

A100-PCIE-40GB^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

CUDA

215,434^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

OpenCL

161,590^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

Vulkan

92,245^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

* Provisional data