GPU Comparison
RADEON
AMD Radeon HD 8670M
CORE STATE
Sun
VRAM
1024 MB
CLOCK SPEED
975 MHz
TDP
—
BUS WIDTH
64 bit
ARCHITECTURE
GCN 1.0
PROCESS
28 nm
LAUNCH DATE
2013
VS
GEFORCE
L40
CORE STATE
AD102
VRAM
48 GB
CLOCK SPEED
2490 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
HD 8670M
L40
Core Specs
Shading Units
320
18,176
+5580.0%
Shaders
320
18,176
+5580.0%
TMUs
20
568
+2740.0%
ROPs
8
192
+2300.0%
Compute Units
5
—
SM Count
—
142
Clocks
Base Clock
925 MHz
735 MHz
Boost Clock
975 MHz
2490 MHz
Memory Clock
900 MHz
1800 Mbps effective
2250 MHz
18 Gbps effective
Memory
Memory Size
1024 MB
48 GB
VRAM (MB)
1,024
49,152
+4700.0%
Memory Type
DDR3
GDDR6
Memory Bus
64 bit
384 bit
Bandwidth
14.40 GB/s
864.0 GB/s
Cache
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
128 KB
96 MB
Performance
Pixel Rate
7.800 GPixel/s
478.1 GPixel/s
Texture Rate
19.50 GTexel/s
1,414.3 GTexel/s
FP32 (TFLOPS)
624.0 GFLOPS
90.52 TFLOPS
FP64 (TFLOPS)
39.00 GFLOPS (1:16)
1,414.3 GFLOPS (1:64)
FP16 (TFLOPS)
—
90.52 TFLOPS (1:1)
AI/RT
RT Cores
—
142
Tensor Cores
—
568
Power
TDP
—
300 W
TDP (W)
—
300
Suggested PSU
—
700 W
Power Connectors
—
1x 16-pin
Architecture
Architecture
GCN 1.0
Ada Lovelace
GPU Name
Sun
AD102
Generation
Solar System
(HD 8600M)
Server Ada
(Lxx)
Process Size
28 nm
5 nm
Transistors
690 million
76,300 million
Die Size
56 mm²
609 mm²
Foundry
TSMC
TSMC
Density
12.3M / mm²
125.3M / mm²
API Support
DirectX
12 (11_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.2.170
1.4
OpenCL
2.1 (1.2)
3.0
CUDA
—
8.9
Shader Model
6.5 (5.1)
6.8
Physical
Slot Width
—
Dual-slot
Length
—
267 mm
10.5 inches
Height
—
111 mm
4.4 inches
Outputs
—
4x DisplayPort 1.4a
Bus Interface
PCIe 3.0 x8
PCIe 4.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
London
Server Ampere
Successor
Gem System
Server Hopper