GPU Comparison
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
PROCESS
28 nm
LAUNCH DATE
2013
VS
GEFORCE
PG506-232
CORE STATE
GA100
VRAM
24 GB
CLOCK SPEED
1440 MHz
TDP
165 W
BUS WIDTH
3072 bit
ARCHITECTURE
Ampere
PROCESS
7 nm
LAUNCH DATE
2021
PERFORMANCE BENCHMARKS
geekbench_opencl
DETAILED SPECIFICATIONS
SPECIFICATION
HD 8970M
PG506-232
Core Specs
Shading Units
1,280
3,584
+180.0%
Shaders
1,280
3,584
+180.0%
TMUs
80
224
+180.0%
ROPs
32
96
+200.0%
Compute Units
20
—
SM Count
—
56
Clocks
Base Clock
850 MHz
930 MHz
Boost Clock
900 MHz
1440 MHz
Memory Clock
1200 MHz
4.8 Gbps effective
1215 MHz
2.4 Gbps effective
Memory
Memory Size
4 GB
24 GB
VRAM (MB)
4,096
24,576
+500.0%
Memory Type
GDDR5
HBM2
Memory Bus
256 bit
3072 bit
Bandwidth
153.6 GB/s
933.1 GB/s
Cache
L1 Cache
16 KB (per CU)
192 KB (per SM)
L2 Cache
512 KB
24 MB
Performance
Pixel Rate
28.80 GPixel/s
138.2 GPixel/s
Texture Rate
72.00 GTexel/s
322.6 GTexel/s
FP32 (TFLOPS)
2.304 TFLOPS
10.32 TFLOPS
FP64 (TFLOPS)
144.0 GFLOPS (1:16)
5.161 TFLOPS (1:2)
FP16 (TFLOPS)
—
10.32 TFLOPS (1:1)
AI/RT
Tensor Cores
—
224
Power
TDP
100 W
165 W
TDP (W)
100
165
+65.0%
Suggested PSU
—
450 W
Power Connectors
—
8-pin EPS
Architecture
Architecture
GCN 1.0
Ampere
GPU Name
Neptune
GA100
Generation
Solar System
(HD 8900M)
Server Ampere
(Axx)
Process Size
28 nm
7 nm
Transistors
2,800 million
54,200 million
Die Size
212 mm²
826 mm²
Foundry
TSMC
TSMC
Density
13.2M / mm²
65.6M / mm²
API Support
DirectX
12 (11_1)
—
OpenGL
4.6
—
Vulkan
1.2.170
—
OpenCL
2.1 (1.2)
3.0
CUDA
—
8.0
Shader Model
6.5 (5.1)
—
Physical
Slot Width
MXM Module
Dual-slot
Length
—
267 mm
10.5 inches
Height
—
112 mm
4.4 inches
Outputs
Portable Device Dependent
No outputs
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
London
Tesla Turing
Successor
Gem System
Server Ada