GPU Comparison
GEFORCE
NVIDIA B200
CORE STATE
GB100
VRAM
90 GB
CLOCK SPEED
1965 MHz
TDP
1000 W
BUS WIDTH
4096 bit
ARCHITECTURE
Blackwell
PROCESS
5 nm
LAUNCH DATE
—
VS
GEFORCE
L40S
CORE STATE
AD102
VRAM
48 GB
CLOCK SPEED
2520 MHz
TDP
300 W
BUS WIDTH
384 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2022
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
B200
L40S
Core Specs
Shading Units
18,944
18,176
-4.1%
Shaders
18,944
18,176
-4.1%
TMUs
592
568
-4.1%
ROPs
24
192
+700.0%
SM Count
148
142
-4.1%
Clocks
Base Clock
700 MHz
1110 MHz
Boost Clock
1965 MHz
2520 MHz
Memory Clock
2000 MHz
8 Gbps effective
2250 MHz
18 Gbps effective
Memory
Memory Size
90 GB
48 GB
VRAM (MB)
92,160
49,152
-46.7%
Memory Type
HBM3e
GDDR6
Memory Bus
4096 bit
384 bit
Bandwidth
4.10 TB/s
864.0 GB/s
Cache
L1 Cache
256 KB (per SM)
128 KB (per SM)
L2 Cache
50 MB
48 MB
Performance
Pixel Rate
47.16 GPixel/s
483.8 GPixel/s
Texture Rate
1,163.3 GTexel/s
1,431.4 GTexel/s
FP32 (TFLOPS)
74.45 TFLOPS
91.61 TFLOPS
FP64 (TFLOPS)
37.22 TFLOPS (1:2)
1,431.4 GFLOPS (1:64)
FP16 (TFLOPS)
1,191.2 TFLOPS (16:1)
91.61 TFLOPS (1:1)
AI/RT
RT Cores
—
142
Tensor Cores
592
568
-4.1%
Power
TDP
1000 W
300 W
TDP (W)
1,000
300
-70.0%
Suggested PSU
1400 W
700 W
Power Connectors
—
1x 16-pin
Architecture
Architecture
Blackwell
Ada Lovelace
GPU Name
GB100
AD102
Generation
Server Blackwell
(Bxx)
Server Ada
(Lxx)
Process Size
5 nm
5 nm
Transistors
104,000 million
76,300 million
Die Size
—
609 mm²
Foundry
TSMC
TSMC
Density
—
125.3M / mm²
API Support
DirectX
—
12 Ultimate (12_2)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
3.0
3.0
CUDA
10.0
8.9
Shader Model
—
6.8
Physical
Slot Width
SXM Module
Dual-slot
Length
—
267 mm
10.5 inches
Height
—
111 mm
4.4 inches
Outputs
No outputs
1x HDMI 2.13x DisplayPort 1.4a
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x16
Other
Production
Active
End-of-life
Predecessor
Server Hopper
Server Ampere
Successor
Server Rubin
Server Hopper