AMD P30PH vs NVIDIA GeForce RTX 4070 Ti SUPER AD102
We compared two Desktop platform GPUs: 4GB VRAM P30PH and 16GB VRAM GeForce RTX 4070 Ti SUPER AD102 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD P30PH 's Advantages
Lower TDP (180W vs 285W)
NVIDIA GeForce RTX 4070 Ti SUPER AD102 's Advantages
Boost Clock has increased by 116% (2610MHz vs 1206MHz)
More VRAM (16GB vs 4GB)
Larger VRAM bandwidth (672.3GB/s vs 268.8GB/s)
6400 additional rendering cores
Score
Benchmark
FP32 (float)
P30PH
4.94 TFLOPS
GeForce RTX 4070 Ti SUPER AD102
+792%
44.1 TFLOPS
Graphics Card
Unknown
Release Date
Jun 2024
Mining GPUs
Generation
GeForce 40
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1120 MHz
Base Clock
2340 MHz
1206 MHz
Boost Clock
2610 MHz
2100 MHz
Memory Clock
1313 MHz
Memory
4GB
Memory Size
16GB
GDDR5
Memory Type
GDDR6X
256bit
Memory Bus
256bit
268.8GB/s
Bandwidth
672.3GB/s
Render Config
32
Compute Units
-
-
SM Count
66
2048
Shading Units
8448
128
TMUs
264
32
ROPs
96
-
Tensor Cores
264
-
RT Cores
66
16 KB (per CU)
L1 Cache
128 KB (per SM)
2 MB
L2 Cache
48 MB
-
-
-
Theoretical Performance
38.59 GPixel/s
Pixel Rate
250.6 GPixel/s
154.4 GTexel/s
Texture Rate
689.0 GTexel/s
4.940 TFLOPS
FP16 (half)
44.10 TFLOPS
4.940 TFLOPS
FP32 (float)
44.10 TFLOPS
308.7 GFLOPS
FP64 (double)
689.0 GFLOPS
Board Design
180W
TDP
285W
450 W
Suggested PSU
600 W
1x HDMI 2.0b
Outputs
1x HDMI 2.13x DisplayPort 1.4a
2x 8-pin
Power Connectors
1x 16-pin
Graphics Processor
Polaris 20
GPU Name
AD102
-
GPU Variant
AD102-175-KEF-A1
GCN 4.0
Architecture
Ada Lovelace
GlobalFoundries
Foundry
TSMC
14 nm
Process Size
5 nm
5.7 billion
Transistors
76.3 billion
232 mm²
Die Size
609 mm²
Graphics Features
12 (12_0)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
2.1
OpenCL
3.0
1.3
Vulkan
1.3
-
CUDA
8.9
6.7
Shader Model
6.8
