GeekRadar / The comparison desk

COMPARE.

GPU

Nvidia

A2

Graphics processor

Video memory: 16 GB^*
Memory bus: 128 bit^*
Rated memory bandwidth: 200.10 GB/s^*

Benchmark results

Geekbench GPU (reported compilation) · version unreported · CUDA38,140^*Platform unreported Compare results
Geekbench GPU (reported compilation) · version unreported · CUDA38,140^*Platform unreported Compare results
Geekbench GPU (reported compilation) · version unreported · OpenCL37,130^*Platform unreported Compare results
Geekbench GPU (reported compilation) · version unreported · OpenCL37,130^*Platform unreported Compare results

Processing & platform

Architecture: Ampere^*
Process node: 8 nm^*
GPU base clock: 1,440 MHz^*
GPU boost clock: 1,770 MHz^*

Memory & storage

Video memory: 16 GB^*
Video memory type: Reported value 1: GDDR5^*
Reported value 2: GDDR6^*
Reported value 3: GDDR6^*
Memory bus: 128 bit^*
Rated memory bandwidth: 200.10 GB/s^*

System configuration

Detailed specifications

Specifications 1 · 19 fields

GPU architecture — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: Ampere^*
Theoretical peak: BF16 tensor dense per GPU — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: 18^* TFLOPS
Theoretical peak: FP16 tensor dense per GPU — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: 18^* TFLOPS
Theoretical peak: FP32 non-tensor dense per GPU — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: 4.5^* TFLOPS
Native hardware support: FP4 tensor — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: No^*
Native hardware support: FP64 tensor — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: No^*
Native hardware support: FP6 tensor — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: No^*
Native hardware support: FP8 tensor — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: No^*
Theoretical peak: INT8 tensor dense per GPU — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: 36^* TOPS
Theoretical peak: TF32 tensor dense per GPU — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: 9^* TFLOPS
Physical configuration — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: PCIe, low-profile, single-slot^*
Native hardware support for GPU interconnect — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: No^*
PCIe interface declaration — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: PCIe Gen4 x8^*
Maximum board power — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: 60^* W
Peak memory bandwidth per GPU — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: 200^* GB/s
Memory interface width per GPU — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: 128^* bit
Memory capacity per GPU — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: 16^* GB
Memory technology — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: GDDR6^*
GPU model — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6: NVIDIA A2 Tensor Core GPU^*

Specifications 2 · 8 fields

Product Name: A2^*
GPU Chip: GA107^*
Released: Nov 10th, 2021^*
Bus: PCIe 4.0 x8^*
Memory: 16 GB, GDDR6, 128 bit^*
GPU clock: 1,440^* MHz
Memory clock: 1,563^* MHz
Shaders TMUs ROPs: 1280 / 40 / 32^*

Specifications 3 · 8 fields

Product Name: A2^*
GPU Chip: GA107^*
Released: Nov 10th, 2021^*
Bus: PCIe 4.0 x8^*
Memory: 16 GB, GDDR6, 128 bit^*
GPU clock: 1,440^* MHz
Memory clock: 1,563^* MHz
Shaders / TMUs / ROPs: 1280 / 40 / 32^*

Specifications 4 · 55 fields

Brand: NVIDIA^*
Top BUS WIDTH: 128^* bit
Graphics Processor GPU Name: GA107^*
Graphics Processor Architecture: Ampere^*
Render Config SM Count: 10^*
Graphics Features CUDA: 8.6^*
Render Config Tensor Cores: 40^*
Graphics Processor Process Size: 8^* nm
Graphics Processor Transistors: 8,700 million^*
Graphics Processor Die Size: 200^* mm²
Graphics Card Release Date: Nov 10th, 2021^*
Graphics Card Generation: Workstation Ampere (Ax000)^*
Graphics Card Successor: Workstation Ada^*
Graphics Card Production: Active^*
Name: A2^*
Graphics Card Bus Interface: PCIe 4.0 x8^*
Clock Speeds Memory Clock: 1563 MHz 12.5 Gbps effective^*
Memory Memory Size: 16^* GB
Memory Memory Type: GDDR6^*
Memory Memory Bus: 128^* bit
Memory Bandwidth: 200.1^* GB/s
Render Config TMUs: 40^*
Top GRAPHICS PROCESSOR: GA107^*
Render Config ROPs: 32^*
Theoretical Performance Pixel Rate: 56.64 GPixel/s
Theoretical Performance Texture Rate: 70.80 GTexel/s
Board Design Slot Width: Single-slot^*
Board Design TDP: 60^* W
Board Design Suggested PSU: 250^* W
Board Design Outputs: No outputs^*
Board Design Board Number: PG179 SKU 220^*
Graphics Features DirectX: 12 Ultimate (12_2)^*
Graphics Features OpenGL: 4.6^*
Graphics Features OpenCL: 3^*
Graphics Features Vulkan: 1.3^*
source file: nvidia2021.json^*
Graphics Processor Foundry: Samsung^*
Graphics Card Predecessor: Quadro Turing^*
Graphics Processor Density: 43.5M / mm²^*
Top TMUS: 40^*
Graphics Processor Chip Package: FCBGA-1358^*
Top ROPS: 32^*
Clock Speeds Base Clock: 1,440^* MHz
Clock Speeds Boost Clock: 1,770^* MHz
Graphics Features Shader Model: 6.8^*
Top CORES: 1,280^*
Render Config Shading Units: 1,280^*
Render Config L2 Cache: 2^* MB
Top MEMORY SIZE: 16^* GB
Theoretical Performance FP32 (float): 4.531^* TFLOPS
Theoretical Performance FP64 (double): 70.80 GFLOPS (1:64)
Render Config L1 Cache: 128 KB (per SM)^*
Theoretical Performance FP16 (half): 4.531 TFLOPS (1:1)
Top MEMORY TYPE: GDDR6^*
Render Config RT Cores: 10^*

Specifications 5 · 4 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

A2^*

Scope and conditions

benchmark_context

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

CUDA

38,140^*

Scope and conditions

benchmark_context

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

OpenCL

37,130^*

Scope and conditions

benchmark_context

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

Specifications 6 · 4 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

A2^*

Scope and conditions

benchmark_context

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

CUDA

38,140^*

Scope and conditions

benchmark_context

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

OpenCL

37,130^*

Scope and conditions

benchmark_context

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

Specifications 7 · 27 fields

manufacturer: NVIDIA^*
manufacturer: NVIDIA^*
rop: 32^*
rop: 40^*
igp: No^*
igp: No^*
bus: PCIe 4.0 x8^*
bus: PCIe 2.0 x16^*
memType: GDDR5^*
memType: GDDR6^*
gpuChip: GA107^*
gpuChip: GF100^*
productName: A2^*
productName: A2^*
releaseYear: 2,021^*
releaseYear: 2,021^*
memSize: 16^*
memSize: 16^*
memBusWidth: 128^*
gpuClock: 1,440^*
gpuClock: 608^*
memClock: 1,563^*
memClock: 837^*
unifiedShader: 1,280^*
unifiedShader: 448^*
tmu: 56^*
tmu: 40^*

* Provisional data