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
P104-100
CORE STATE
GP104
VRAM
4 GB
CLOCK SPEED
1733 MHz
TDP
—
BUS WIDTH
256 bit
ARCHITECTURE
Pascal
PROCESS
16 nm
LAUNCH DATE
2017
PERFORMANCE BENCHMARKS
geekbench_opencl
3dmark_3dmark_steel_nomad_dx12
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
B200
P104-100
Core Specs
Shading Units
18,944
1,920
-89.9%
Shaders
18,944
1,920
-89.9%
TMUs
592
120
-79.7%
ROPs
24
64
+166.7%
SM Count
148
15
-89.9%
Clocks
Base Clock
700 MHz
1607 MHz
Boost Clock
1965 MHz
1733 MHz
Memory Clock
2000 MHz
8 Gbps effective
1251 MHz
10 Gbps effective
Memory
Memory Size
90 GB
4 GB
VRAM (MB)
92,160
4,096
-95.6%
Memory Type
HBM3e
GDDR5X
Memory Bus
4096 bit
256 bit
Bandwidth
4.10 TB/s
320.3 GB/s
Cache
L1 Cache
256 KB (per SM)
48 KB (per SM)
L2 Cache
50 MB
2 MB
Performance
Pixel Rate
47.16 GPixel/s
110.9 GPixel/s
Texture Rate
1,163.3 GTexel/s
208.0 GTexel/s
FP32 (TFLOPS)
74.45 TFLOPS
6.655 TFLOPS
FP64 (TFLOPS)
37.22 TFLOPS (1:2)
208.0 GFLOPS (1:32)
FP16 (TFLOPS)
1,191.2 TFLOPS (16:1)
104.0 GFLOPS (1:64)
AI/RT
Tensor Cores
592
—
Power
TDP
1000 W
—
TDP (W)
1,000
—
Suggested PSU
1400 W
200 W
Power Connectors
—
1x 8-pin
Architecture
Architecture
Blackwell
Pascal
GPU Name
GB100
GP104
Generation
Server Blackwell
(Bxx)
Mining GPUs
Process Size
5 nm
16 nm
Transistors
104,000 million
7,200 million
Die Size
—
314 mm²
Foundry
TSMC
TSMC
Density
—
22.9M / mm²
API Support
DirectX
—
12 (12_1)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
3.0
3.0
CUDA
10.0
6.1
Shader Model
—
6.8
Physical
Slot Width
SXM Module
Dual-slot
Length
—
267 mm
10.5 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 5.0 x16
PCIe 1.0 x4
Other
Production
Active
End-of-life
Predecessor
Server Hopper
—
Successor
Server Rubin
—