AMD Radeon PRO W9070 vs NVIDIA A100 SXM4 40 GB
GPU Specs Compare
Graphics Card
Release Date
Unknown
May 2020
Generation
Mining GPUs
Tesla Ampere
Type
Desktop
AI GPU
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
1120 MHz
1095 MHz
Boost Clock
1206 MHz
1410 MHz
Memory Clock
2100 MHz
1215 MHz
Memory
Memory Size
4GB
40GB
Memory Type
GDDR5
HBM2e
Memory Bus
256bit
5120bit
Bandwidth
268.8GB/s
1555GB/s
Render Config
Compute Units
32
-
Shading Units
2048
6912
TMUs
128
432
ROPs
32
160
Tensor Cores
128
432
RT Cores
64
-
L1 Cache
16 KB (per CU)
192 KB (per SM)
L2 Cache
2 MB
40 MB
L3 Cache
64 MB
-
SM Count
-
108
Theoretical Performance
Pixel Rate
38.59 GPixel/s
225.6 GPixel/s
Texture Rate
154.4 GTexel/s
609.1 GTexel/s
FP16 (half)
4.940 TFLOPS
77.97 TFLOPS
FP32 (float)
4.940 TFLOPS
19.49 TFLOPS
FP64 (double)
308.7 GFLOPS
9.746 TFLOPS
Graphics Processor
GPU Name
Polaris 20
GA100
GPU Variant
Navi 48 XTW
-
Architecture
GCN 4.0
Ampere
Foundry
GlobalFoundries
TSMC
Process Size
14 nm
7 nm
Transistors
5.7 billion
54.2 billion
Die Size
232 mm²
826 mm²
Board Design
TDP
180W
400W
Suggested PSU
450 W
800 W
Outputs
1x HDMI 2.0b
No outputs
Power Connectors
2x 8-pin
None
Graphics Features
DirectX
12 (12_0)
N/A
OpenGL
4.6
N/A
OpenCL
2.1
3.0
Vulkan
1.3
N/A
Shader Model
6.7
N/A
CUDA
-
8.0
📊 Benchmark
Blender
-
2,186