Radeon RX 6600 vs A40 PCIe
We compared two Desktop platform GPUs: 8GB VRAM Radeon RX 6600 and 48GB VRAM A40 PCIe to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Radeon RX 6600 's Advantages
Released 1 years late
Boost Clock has increased by 43% (2491MHz vs 1740MHz)
Lower TDP (132W vs 300W)
A40 PCIe 's Advantages
More VRAM (48GB vs 8GB)
Larger VRAM bandwidth (695.8GB/s vs 224.0GB/s)
8960 additional rendering cores
Score
Benchmark
FP32 (float)
Radeon RX 6600
8928
A40 PCIe
+319%
37420
Graphics Card
Oct 2021
Release Date
Oct 2020
Navi II
Generation
Tesla
Desktop
Type
Desktop
PCIe 4.0 x8
Bus Interface
PCIe 4.0 x16
Clock Speeds
1626 MHz
Base Clock
1305 MHz
2491 MHz
Boost Clock
1740 MHz
1750 MHz
Memory Clock
1812 MHz
Memory
8GB
Memory Size
48GB
GDDR6
Memory Type
GDDR6
128bit
Memory Bus
384bit
224.0GB/s
Bandwidth
695.8GB/s
Render Config
28
Compute Units
-
-
SM Count
84
1792
Shading Units
10752
112
TMUs
336
64
ROPs
112
-
Tensor Cores
336
28
RT Cores
84
128 KB per Array
L1 Cache
128 KB (per SM)
2 MB
L2 Cache
6 MB
32 MB
L3 Cache
-
Theoretical Performance
159.4 GPixel/s
Pixel Rate
194.9 GPixel/s
279.0 GTexel/s
Texture Rate
584.6 GTexel/s
17.86 TFLOPS
FP16 (half)
37.42 TFLOPS
8.928 TFLOPS
FP32 (float)
37.42 TFLOPS
558.0 GFLOPS
FP64 (double)
584.6 GFLOPS
Board Design
132W
TDP
300W
300 W
Suggested PSU
700 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
3x DisplayPort 1.4a
1x 8-pin
Power Connectors
8-pin EPS
Graphics Processor
Navi 23
GPU Name
GA102
Navi 23 XL
(215-130000016)
GPU Variant
-
RDNA 2.0
Architecture
Ampere
TSMC
Foundry
Samsung
7 nm
Process Size
8 nm
11.06 billion
Transistors
28.3 billion
237 mm²
Die Size
628 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
2.1
OpenCL
3.0
1.3
Vulkan
1.3
-
CUDA
8.6
6.5
Shader Model
6.6
