GPU Comparison

AMD
RADEON

AMD Radeon HD 8970M

CORE STATE Neptune
VRAM 4 GB
CLOCK SPEED 900 MHz
TDP 100 W
BUS WIDTH 256 bit
ARCHITECTURE GCN 1.0
nm
PROCESS 28 nm
LAUNCH DATE 2013
VS
NVIDIA
GEFORCE

B200

CORE STATE GB100
VRAM 90 GB
CLOCK SPEED 1965 MHz
TDP 1000 W
BUS WIDTH 4096 bit
ARCHITECTURE Blackwell
nm
PROCESS 5 nm
LAUNCH DATE

PERFORMANCE BENCHMARKS

geekbench_opencl
21,237
345,482

DETAILED SPECIFICATIONS

SPECIFICATION
HD 8970M
B200
Core Specs
Shading Units
1,280
18,944 +1380.0%
Shaders
1,280
18,944 +1380.0%
TMUs
80
592 +640.0%
ROPs
32
24 -25.0%
Compute Units
20
SM Count
148
Clocks
Base Clock
850 MHz
700 MHz
Boost Clock
900 MHz
1965 MHz
Memory Clock
1200 MHz 4.8 Gbps effective
2000 MHz 8 Gbps effective
Memory
Memory Size
4 GB
90 GB
VRAM (MB)
4,096
92,160 +2150.0%
Memory Type
GDDR5
HBM3e
Memory Bus
256 bit
4096 bit
Bandwidth
153.6 GB/s
4.10 TB/s
Cache
L1 Cache
16 KB (per CU)
256 KB (per SM)
L2 Cache
512 KB
50 MB
Performance
Pixel Rate
28.80 GPixel/s
47.16 GPixel/s
Texture Rate
72.00 GTexel/s
1,163.3 GTexel/s
FP32 (TFLOPS)
2.304 TFLOPS
74.45 TFLOPS
FP64 (TFLOPS)
144.0 GFLOPS (1:16)
37.22 TFLOPS (1:2)
FP16 (TFLOPS)
1,191.2 TFLOPS (16:1)
AI/RT
Tensor Cores
592
Power
TDP
100 W
1000 W
TDP (W)
100
1,000 +900.0%
Suggested PSU
1400 W
Architecture
Architecture
GCN 1.0
Blackwell
GPU Name
Neptune
GB100
Generation
Solar System (HD 8900M)
Server Blackwell (Bxx)
Process Size
28 nm
5 nm
Transistors
2,800 million
104,000 million
Die Size
212 mm²
Foundry
TSMC
TSMC
Density
13.2M / mm²
API Support
DirectX
12 (11_1)
OpenGL
4.6
Vulkan
1.2.170
OpenCL
2.1 (1.2)
3.0
CUDA
10.0
Shader Model
6.5 (5.1)
Physical
Slot Width
MXM Module
SXM Module
Outputs
Portable Device Dependent
No outputs
Bus Interface
PCIe 3.0 x16
PCIe 5.0 x16
Other
Production
End-of-life
Active
Predecessor
London
Server Hopper
Successor
Gem System
Server Rubin
View Radeon HD 8970M Details View B200 Details