GPU Comparison

NVIDIA
GEFORCE

NVIDIA H200 NVL

CORE STATE GH100
VRAM 141 GB
CLOCK SPEED 1785 MHz
TDP 600 W
BUS WIDTH 6144 bit
ARCHITECTURE Hopper
nm
PROCESS 5 nm
LAUNCH DATE 2024
VS
NVIDIA
GEFORCE

Tesla M40

CORE STATE GM200
VRAM 12 GB
CLOCK SPEED 1112 MHz
TDP 250 W
BUS WIDTH 384 bit
ARCHITECTURE Maxwell 2.0
nm
PROCESS 28 nm
LAUNCH DATE 2015

PERFORMANCE BENCHMARKS

geekbench_opencl
305,608
39,192
geekbench_vulkan
N/A
44,602

DETAILED SPECIFICATIONS

SPECIFICATION
H200 NVL
Tesla M40
Core Specs
Shading Units
16,896
3,072 -81.8%
Shaders
16,896
3,072 -81.8%
TMUs
528
192 -63.6%
ROPs
24
96 +300.0%
SM Count
132
Clocks
Base Clock
1365 MHz
948 MHz
Boost Clock
1785 MHz
1112 MHz
Memory Clock
1593 MHz 6.4 Gbps effective
1502 MHz 6 Gbps effective
Memory
Memory Size
141 GB
12 GB
VRAM (MB)
144,384
12,288 -91.5%
Memory Type
HBM3e
GDDR5
Memory Bus
6144 bit
384 bit
Bandwidth
4.89 TB/s
288.4 GB/s
Cache
L1 Cache
256 KB (per SM)
48 KB (per SMM)
L2 Cache
50 MB
3 MB
Performance
Pixel Rate
42.84 GPixel/s
106.8 GPixel/s
Texture Rate
942.5 GTexel/s
213.5 GTexel/s
FP32 (TFLOPS)
60.32 TFLOPS
6.832 TFLOPS
FP64 (TFLOPS)
30.16 TFLOPS (1:2)
213.5 GFLOPS (1:32)
FP16 (TFLOPS)
241.3 TFLOPS (4:1)
AI/RT
Tensor Cores
528
Power
TDP
600 W
250 W
TDP (W)
600
250 -58.3%
Suggested PSU
1000 W
600 W
Power Connectors
8-pin EPS
8-pin EPS
Architecture
Architecture
Hopper
Maxwell 2.0
GPU Name
GH100
GM200
Generation
Server Hopper (Hxx)
Tesla Maxwell (Mxx)
Process Size
5 nm
28 nm
Transistors
80,000 million
8,000 million
Die Size
814 mm²
601 mm²
Foundry
TSMC
TSMC
Density
98.3M / mm²
13.3M / mm²
API Support
DirectX
12 (12_1)
OpenGL
4.6
Vulkan
1.4
OpenCL
3.0
3.0
CUDA
9.0
5.2
Shader Model
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm 10.5 inches
267 mm 10.5 inches
Height
111 mm 4.4 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Other
Production
Active
End-of-life
Predecessor
Server Ada
Tesla Kepler
Successor
Server Blackwell
Tesla Pascal
View H200 NVL Details View Tesla M40 Details