Home GPU Comparison NVIDIA H100 SXM5 64 GB vs NVIDIA Tesla K40st

NVIDIA H100 SXM5 64 GB vs NVIDIA Tesla K40st

AI GPU We compared a GPU: 64GB VRAM H100 SXM5 64 GB and a Professional market GPU: 12GB VRAM Tesla K40st to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA H100 SXM5 64 GB 's Advantages
Released 9 years and 4 months late
Boost Clock1980MHz
More VRAM (64GB vs 12GB)
Larger VRAM bandwidth (1008GB/s vs 288.4GB/s)
14016 additional rendering cores
NVIDIA Tesla K40st 's Advantages
Lower TDP (245W vs 700W)

Score

Benchmark

FP32 (float)
H100 SXM5 64 GB +1920%
66.91 TFLOPS
Tesla K40st
3.312 TFLOPS
VS

Graphics Card

Mar 2023
Release Date
Nov 2013
Tesla Hopper
Generation
Tesla
AI GPU
Type
Professional
PCIe 5.0 x16
Bus Interface
PCIe 3.0 x16

Clock Speeds

1665 MHz
Base Clock
-
1980 MHz
Boost Clock
-
1313 MHz
Memory Clock
1502 MHz

Memory

64GB
Memory Size
12GB
HBM3
Memory Type
GDDR5
3072bit
Memory Bus
384bit
1008GB/s
Bandwidth
288.4GB/s

Render Config

132
SM Count
-
-
Compute Units
-
16896
Shading Units
2880
528
TMUs
240
24
ROPs
48
528
Tensor Cores
-
-
RT Cores
-
256 KB (per SM)
L1 Cache
16 KB (per SMX)
50 MB
L2 Cache
1536 KB

Theoretical Performance

47.52 GPixel/s
Pixel Rate
34.50 GPixel/s
1045 GTexel/s
Texture Rate
138.0 GTexel/s
267.6 TFLOPS
FP16 (half)
-
66.91 TFLOPS
FP32 (float)
3.312 TFLOPS
33.45 TFLOPS
FP64 (double)
1104 GFLOPS

Graphics Processor

GH100
GPU Name
GK110B
-
GPU Variant
-
Hopper
Architecture
Kepler
TSMC
Foundry
TSMC
4 nm
Process Size
28 nm
80 billion
Transistors
7.08 billion
814 mm²
Die Size
561 mm²

Board Design

700W
TDP
245W
1100 W
Suggested PSU
550 W
No outputs
Outputs
No outputs
8-pin EPS
Power Connectors
-

Graphics Features

N/A
DirectX
12 (11_1)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.1
9.0
CUDA
3.5
N/A
Shader Model
5.1

Related GPU Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy