GPU Comparison
RADEON
AMD Radeon HD 6850 X2
CORE STATE
Barts
VRAM
2 GB
CLOCK SPEED
—
TDP
254 W
BUS WIDTH
256 bit
ARCHITECTURE
TeraScale 2
PROCESS
40 nm
LAUNCH DATE
2011
VS
GEFORCE
RTX 5000 Mobile Ada Generation
CORE STATE
AD103
VRAM
16 GB
CLOCK SPEED
2115 MHz
TDP
120 W
BUS WIDTH
256 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2023
PERFORMANCE BENCHMARKS
geekbench_opencl
3dmark_3dmark_steel_nomad_dx12
DETAILED SPECIFICATIONS
SPECIFICATION
HD 6850 X2
RTX 5000 Mobile Ada Generation
Core Specs
Shading Units
960
9,728
+913.3%
Shaders
960
9,728
+913.3%
TMUs
48
304
+533.3%
ROPs
32
112
+250.0%
Compute Units
12
—
SM Count
—
76
Clocks
Base Clock
—
1425 MHz
Boost Clock
—
2115 MHz
GPU Clock
800 MHz
—
Memory Clock
1050 MHz
4.2 Gbps effective
2250 MHz
18 Gbps effective
Memory
Memory Size
2 GB
16 GB
VRAM (MB)
2,048
16,384
+700.0%
Memory Type
GDDR5
GDDR6
Memory Bus
256 bit
256 bit
Bandwidth
134.4 GB/s
576.0 GB/s
Cache
L1 Cache
8 KB (per CU)
128 KB (per SM)
L2 Cache
512 KB
64 MB
Performance
Pixel Rate
25.60 GPixel/s
236.9 GPixel/s
Texture Rate
38.40 GTexel/s
643.0 GTexel/s
FP32 (TFLOPS)
1.536 TFLOPS
41.15 TFLOPS
FP64 (TFLOPS)
—
643.0 GFLOPS (1:64)
FP16 (TFLOPS)
—
41.15 TFLOPS (1:1)
AI/RT
RT Cores
—
76
Tensor Cores
—
304
Power
TDP
254 W
120 W
TDP (W)
254
120
-52.8%
Suggested PSU
600 W
—
Power Connectors
2x 8-pin
None
Architecture
Architecture
TeraScale 2
Ada Lovelace
GPU Name
Barts
AD103
Generation
Northern Islands
(HD 6800)
Ada-MW
(x000A)
Process Size
40 nm
5 nm
Transistors
1,700 million
45,900 million
Die Size
255 mm²
379 mm²
Foundry
TSMC
TSMC
Density
6.7M / mm²
121.1M / mm²
API Support
DirectX
11.2 (11_0)
12 Ultimate (12_2)
OpenGL
4.4
4.6
Vulkan
—
1.4
OpenCL
1.2
3.0
CUDA
—
8.9
Shader Model
5.0
6.8
Physical
Slot Width
Dual-slot
IGP
Outputs
2x DVI1x HDMI 1.3a1x DisplayPort 1.1
Portable Device Dependent
Bus Interface
PCIe 2.0 x16
PCIe 4.0 x16
Other
Production
End-of-life
Active
Predecessor
Evergreen
Ampere-MW
Successor
Southern Islands
Blackwell-MW