Radeon HD 4670 AGP vs NVIDIA P104 100 8 GB
We compared two Desktop platform GPUs: 1024MB VRAM Radeon HD 4670 AGP and 48GB
GB VRAM NVIDIA P104 100 8 GB to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Radeon HD 4670 AGP 's Advantages
More VRAM (1024GB vs 48GB)
NVIDIA P104 100 8 GB 's Advantages
Released 8 years and 5 months late
Boost Clock1733MHz
Larger VRAM bandwidth (320.3GB/s vs 25.60GB/s)
1600 additional rendering cores
Score
Benchmark
FP32 (float)
Radeon HD 4670 AGP
480
NVIDIA P104 100 8 GB
+1286%
6655
Graphics Card
Jul 2009
Release Date
Dec 2017
Radeon R700
Generation
Mining GPUs
Desktop
Type
Desktop
AGP 8x
Bus Interface
PCIe 1.0 x4
Clock Speeds
-
Base Clock
1607 MHz
-
Boost Clock
1733 MHz
800 MHz
Memory Clock
1251 MHz
Memory
1024MB
Memory Size
48GB
GB
GDDR3
Memory Type
GDDR5X
128bit
Memory Bus
256bit
25.60GB/s
Bandwidth
320.3GB/s
Render Config
4
Compute Units
-
-
SM Count
15
320
Shading Units
1920
32
TMUs
120
8
ROPs
64
16 KB (per CU)
L1 Cache
48 KB (per SM)
128 KB
L2 Cache
2 MB
Theoretical Performance
6.000 GPixel/s
Pixel Rate
110.9 GPixel/s
24.00 GTexel/s
Texture Rate
208.0 GTexel/s
-
FP16 (half)
104.0 GFLOPS
480.0 GFLOPS
FP32 (float)
6.655 TFLOPS
-
FP64 (double)
208.0 GFLOPS
Board Design
59W
TDP
Unknown
250 W
Suggested PSU
200 W
1x DVI
1x HDMI 1.3a
1x VGA
Outputs
No outputs
-
Power Connectors
1x 8-pin
Graphics Processor
RV730
GPU Name
GP104
RV730 XT
(215-0719047)
GPU Variant
GP104-100-A1
TeraScale
Architecture
Pascal
TSMC
Foundry
TSMC
55 nm
Process Size
16 nm
0.514 billion
Transistors
7.2 billion
146 mm²
Die Size
314 mm²
Graphics Features
10.1 (10_1)
DirectX
12 (12_1)
3.3
OpenGL
4.6
1.1
OpenCL
3.0
N/A
Vulkan
1.3
-
CUDA
6.1
4.1
Shader Model
6.8
