P102 100 vs Radeon HD 6770
We compared two Desktop platform GPUs: 5GB VRAM P102 100 and 1024MB VRAM Radeon HD 6770 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
P102 100 Advantages
Released 7 years and 1 months late
Boost Clock1683MHz
More VRAM (5GB vs 1024GB)
Larger VRAM bandwidth (440.3GB/s vs 76.80GB/s)
2400 additional rendering cores
Radeon HD 6770 Advantages
Lower TDP (108W vs 250W)
Score
Benchmark
FP32 (float)
P102 100
+691%
10770
Radeon HD 6770
1360
3DMark Time Spy
P102 100
+79%
7042
Radeon HD 6770
3924
Graphics Card
Feb 2018
Release Date
Jan 2011
Mining GPUs
Generation
Northern Islands
Desktop
Type
Desktop
PCIe 3.0 x4
Bus Interface
PCIe 2.0 x16
Clock Speeds
1582 MHz
Base Clock
-
1683 MHz
Boost Clock
-
1376 MHz
Memory Clock
1200 MHz
Memory
5GB
Memory Size
1024MB
GDDR5X
Memory Type
GDDR5
320bit
Memory Bus
128bit
440.3GB/s
Bandwidth
76.80GB/s
Render Config
-
Compute Units
10
25
SM Count
-
3200
Shading Units
800
200
TMUs
40
80
ROPs
16
48 KB (per SM)
L1 Cache
8 KB (per CU)
0 MB
L2 Cache
256 KB
Theoretical Performance
134.6 GPixel/s
Pixel Rate
13.60 GPixel/s
336.6 GTexel/s
Texture Rate
34.00 GTexel/s
168.3 GFLOPS
FP16 (half)
-
10.77 TFLOPS
FP32 (float)
1360 GFLOPS
336.6 GFLOPS
FP64 (double)
-
Board Design
250W
TDP
108W
600 W
Suggested PSU
300 W
No outputs
Outputs
2x DVI
1x HDMI 1.3a
2x mini-DisplayPort 1.1
1x HDMI 1.3a
2x mini-DisplayPort 1.1
2x 8-pin
Power Connectors
1x 6-pin
Graphics Processor
GP102
GPU Name
Juniper
GP102-100-A1
GPU Variant
Juniper XT
(215-0754013)
(215-0754013)
Pascal
Architecture
TeraScale 2
TSMC
Foundry
TSMC
16 nm
Process Size
40 nm
11.8 billion
Transistors
1.04 billion
471 mm²
Die Size
166 mm²
Graphics Features
12 (12_1)
DirectX
11.2 (11_0)
4.6
OpenGL
4.4
3.0
OpenCL
1.2
1.3
Vulkan
N/A
6.1
CUDA
-
6.4
Shader Model
5.0