Home GPU Comparison NVIDIA B200 SXM 192 GB vs AMD Radeon HD 7670 OEM

NVIDIA B200 SXM 192 GB vs AMD Radeon HD 7670 OEM

We compared two Desktop platform GPUs: 192GB VRAM B200 SXM 192 GB and 512MB VRAM Radeon HD 7670 OEM to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA B200 SXM 192 GB 's Advantages
Released 12 years late
Boost Clock1837MHz
More VRAM (192GB vs 512GB)
Larger VRAM bandwidth (4100GB/s vs 64.00GB/s)
16416 additional rendering cores
AMD Radeon HD 7670 OEM 's Advantages
Lower TDP (66W vs 1000W)

Score

Benchmark

FP32 (float)
B200 SXM 192 GB +7983%
62.08 TFLOPS
Radeon HD 7670 OEM
0.768 TFLOPS
VS

Graphics Card

Jan 2024
Release Date
Jan 2012
Tesla Blackwell
Generation
Southern Islands
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 2.0 x16

Clock Speeds

1665 MHz
Base Clock
-
1837 MHz
Boost Clock
-
2000 MHz
Memory Clock
1000 MHz

Memory

192GB
Memory Size
512MB
HBM3e
Memory Type
GDDR5
4096bit
Memory Bus
128bit
4100GB/s
Bandwidth
64.00GB/s

Render Config

-
Compute Units
6
132
SM Count
-
16896
Shading Units
480
528
TMUs
24
24
ROPs
8
528
Tensor Cores
-
-
-
-
256 KB (per SM)
L1 Cache
8 KB (per CU)
50 MB
L2 Cache
256 KB
-
-
-

Theoretical Performance

44.09 GPixel/s
Pixel Rate
6.400 GPixel/s
969.9 GTexel/s
Texture Rate
19.20 GTexel/s
248.3 TFLOPS
FP16 (half)
-
62.08 TFLOPS
FP32 (float)
768.0 GFLOPS
31.04 TFLOPS
FP64 (double)
-

Board Design

1000W
TDP
66W
1400 W
Suggested PSU
250 W
No outputs
Outputs
1x DVI 1x DisplayPort 1.1 1x VGA
-
Power Connectors
None

Graphics Processor

GB100
GPU Name
Turks
-
GPU Variant
Turks XT (215-0803000)
Blackwell
Architecture
TeraScale 2
TSMC
Foundry
TSMC
5 nm
Process Size
40 nm
208 billion
Transistors
0.716 billion
Unknown
Die Size
118 mm²

Graphics Features

N/A
DirectX
11.2 (11_0)
N/A
OpenGL
4.4
3.0
OpenCL
1.2
N/A
Vulkan
N/A
9.0
CUDA
-
N/A
Shader Model
5.0

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy