AMD Radeon R7 265X OEM vs NVIDIA H100 SXM5

GPU · Specs Compare

Products
GPU AMD Radeon R7 265X OEM AMD · 2014-08
GPU NVIDIA H100 SXM5 NVIDIA · 2022-03
Graphics Card
Release Date
Aug 2014
Mar 2022
Generation
Volcanic Islands
Tesla Hopper
Type
Desktop
AI GPU
Bus Interface
PCIe 3.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
900 MHz
1590 MHz
Boost Clock
925 MHz
1980 MHz
Memory Clock
1400 MHz
1313 MHz
Memory
Memory Size
2GB
80GB
Memory Type
GDDR5
HBM3
Memory Bus
256bit
5120bit
Bandwidth
179.2GB/s
3350GB/s
Render Config
Compute Units
20
—
Shading Units
1280
16896
TMUs
80
528
ROPs
32
24
L1 Cache
16 KB (per CU)
256 KB (per SM)
L2 Cache
512 KB
50 MB
SM Count
—
132
Tensor Cores
—
528
Theoretical Performance
Pixel Rate
29.60 GPixel/s
47.52 GPixel/s
Texture Rate
74.00 GTexel/s
1045 GTexel/s
FP32 (float)
2.368 TFLOPS
66.91 TFLOPS
FP64 (double)
148.0 GFLOPS
33.45 TFLOPS
FP16 (half)
—
267.6 TFLOPS
Graphics Processor
GPU Name
Curacao
GH100
GPU Variant
Curacao PRO(215-0848000)
—
Architecture
GCN 1.0
Hopper
Foundry
TSMC
TSMC
Process Size
28 nm
4 nm
Transistors
2.8 billion
80 billion
Die Size
212 mm²
814 mm²
Board Design
TDP
150W
700W
Suggested PSU
450 W
1100 W
Outputs
2x DVI1x HDMI 1.4a1x DisplayPort 1.2
No outputs
Power Connectors
1x 6-pin
8-pin EPS
Graphics Features
DirectX
12 (11_1)
N/A
OpenGL
4.6
N/A
OpenCL
1.2
3.0
Vulkan
1.2
N/A
Shader Model
5.1
N/A
CUDA
—
9.0
▲ Specs Compare Data sourced from official specifications and benchmark tests.