NVIDIA 2x GeForce RTX 4090 vs AMD Radeon RX 540
NVIDIA 2x GeForce RTX 4090
$3,198
AMD Radeon RX 540
|
2x 16384 Shaders
48GB (2x 24GB) GDDR6X
2520MHz
|
512 Shaders
2GB GDDR5
1219MHz
|
|
Peak AI Performance
5.28 POPS
INT4 Tensor Sparse
|
Peak AI Performance
1.25 TFLOPS
FP16
|
|
FP32
165.15 TFLOPS
|
FP32
1.25 TFLOPS
|
|
FP16
165.15 TFLOPS
|
FP16
1.25 TFLOPS
|
|
Form Factor
PCIe Card
2x 3.0-Slots
|
Form Factor
PCIe Card
2.0-Slots
|
|
TDP
900W
|
TDP
Unknown
|
|
Power Connectors
-
-
-
1x 16-Pin 12VHPWR
|
-
-
-
-
-
|
|
GB6 OpenCL N/A
0%
|
|
|
GB6 Metal N/A
0%
|
GB6 Metal N/A
0%
|
|
GB6 Vulkan N/A
0%
|
GB6 Vulkan N/A
0%
|
|
GB5 OpenCL N/A
0%
|
GB5 OpenCL N/A
0%
|
|
GB5 CUDA N/A
0%
|
GB5 CUDA N/A
0%
|
|
GB5 Metal N/A
0%
|
GB5 Metal N/A
0%
|
|
GB5 Vulkan N/A
0%
|
GB5 Vulkan N/A
0%
|
|
OCT 2020.1 N/A
0%
|
OCT 2020.1 N/A
0%
|
|
OCT Metal N/A
0%
|
OCT Metal N/A
0%
|
|
Peak AI
Performance
5.28 POPS
INT4 Tensor Sparse
|
Peak AI
Performance
1.25 TFLOPS
FP16
|
|
-
-
-
|
-
-
-
|
|
FP8
-
1.32 PFLOPS
Tensor (FP16 Accumulate)
2.64 PFLOPS
Tensor (FP16 Accumulate) Sparse
660.6 TFLOPS
Tensor (FP32 Accumulate)
1.32 PFLOPS
Tensor (FP32 Accumulate) Sparse
|
-
-
-
-
-
-
|
|
FP16
165.15 TFLOPS
660.6 TFLOPS
Tensor (FP16 Accumulate)
1.32 PFLOPS
Tensor (FP16 Accumulate) Sparse
330.3 TFLOPS
Tensor (FP32 Accumulate)
660.6 TFLOPS
Tensor (FP32 Accumulate) Sparse
|
FP16
1.25 TFLOPS
-
-
-
-
|
|
FP32
165.15 TFLOPS
-
-
|
FP32
1.25 TFLOPS
-
-
|
|
FP64
2.58 TFLOPS
-
|
FP64
80 GFLOPS
-
|
|
BF16
165.15 TFLOPS
330.3 TFLOPS
Tensor
660.6 TFLOPS
Tensor Sparse
|
-
-
-
-
|
|
TF32
165.15 TFLOPS
Tensor
330.3 TFLOPS
Tensor Sparse
|
-
-
-
|
|
INT4
2.64 POPS
Tensor
5.28 POPS
Tensor Sparse
|
-
-
-
|
|
INT8
-
1.32 POPS
Tensor
2.64 POPS
Tensor Sparse
|
-
-
-
-
|
|
INT32
82.58 TOPS
|
-
-
|
|
Ray Tracing
190.9 TOPS
|
-
-
|
|
Pixel
Fillrate
443.52 GPixel/s
|
Pixel
Fillrate
19.504 GPixel/s
|
|
-
-
|
-
-
|
|
Texture
Fillrate
1290.24 GTexel/s
|
Texture
Fillrate
39.008 GTexel/s
|
|
Manufacturer
NVIDIA
|
Manufacturer
AMD
|
|
Chip Designer
NVIDIA
|
Chip Designer
AMD
|
|
Architecture
Ada Lovelace
|
Architecture
GCN 4
|
|
Family
GeForce 40
|
Family
Radeon RX 500
|
|
Codename
NV182
AD102
Variant
AD102-300-A1
|
Codename
Lexa
Polaris 12
Variant
Polaris 12 XL
|
|
Market Segment
Desktop
|
Market Segment
Desktop
|
|
Release Date
10/12/2022
|
Release Date
4/18/2017
|
|
Foundry
TSMC
-
|
Foundry
GlobalFoundries
-
|
|
Fabrication Node
4N
-
|
Fabrication Node
14LPP
-
|
|
Die Size
2x 608 mm²
-
|
Die Size
103 mm²
-
|
|
Transistor Count
2x 76.3 Billion
-
|
Transistor Count
2.2 Billion
-
|
|
Transistor Density
125.41M/mm²
-
|
Transistor Density
21.36M/mm²
-
|
|
Form
PCIe Card
|
Form
PCIe Card
|
|
Shading Units
2x 16384 Shaders
-
|
Shading Units
512 Shaders
-
|
|
Texture Mapping Units
2x 512 TMUs
|
Texture Mapping Units
32 TMUs
|
|
Render Output Units
2x 176 ROPs
|
Render Output Units
16 ROPs
|
|
Tensor Cores
2x 512 T-Cores
|
-
-
|
|
Ray-Tracing Cores
2x 128 RT-Cores
|
-
-
|
|
Streaming Multiprocessors
2x 128 SMs
|
-
-
|
|
-
-
|
Compute Units
8 CUs
|
|
-
-
|
-
-
|
|
Graphics Processing Clusters
2x 11 GPCs
|
-
-
|
|
-
-
2230MHz Base
2520MHz
|
-
-
1124MHz Base
1219MHz
|
|
-
-
|
-
-
|
|
L1
64KB/SM Tex
128KB/SM
-
-
|
L1
-
-
16KB/CU
-
|
|
L2
72MB Shared
|
L2
512KB Shared
|
|
-
-
-
|
-
-
-
|
|
48GB (2x 24GB)
GDDR6X
-
|
2GB
GDDR5
-
|
|
Bus Width
384Bit
|
Bus Width
128Bit
|
|
Clock
1313MHz
Transfer Rate
21GT/s
Bandwidth
1008GB/s
|
Clock
1500MHz
Transfer Rate
6GT/s
Bandwidth
96GB/s
|
|
-
-
-
-
-
-
-
-
-
|
-
-
-
-
-
-
-
-
-
|
|
TDP
900W
|
TDP
Unknown
|
|
Temp
90°C Max
|
-
-
|
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
6x DisplayPort 1.4
-
-
-
-
-
-
-
-
-
-
-
2x HDMI 2.1
-
-
|
-
-
-
-
-
-
-
-
-
-
1x DVI-D Dual-Link
-
-
-
-
-
-
-
-
-
-
-
-
-
1x DisplayPort 1.4
-
-
-
-
-
-
-
-
-
-
1x HDMI 2.0
-
-
-
|
|
Max Resolution
7680x4320
|
Max Resolution
5120x2880
|
|
Max Resolution Refresh Rate
60Hz
|
Max Resolution Refresh Rate
60Hz
|
|
Variable Refresh Rate
G-Sync
FreeSync
-
|
Variable Refresh Rate
-
FreeSync
-
|
|
Display Stream Compression (DSC)
Supported
|
Display Stream Compression (DSC)
Not Supported
|
|
Multi Monitor Support
4
|
Multi Monitor Support
3
|
|
Content Protection
HDCP 2.3
|
Content Protection
HDCP 2.2
|
|
Model
2x NVENC 8
|
Model
VCE 3.4
|
|
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
|
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
|
|
Model
NVDEC 5
|
Model
UVD 6.3
|
|
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
|
Codec
MPEG-1
MPEG-2
MPEG-4
JPEG
VC-1
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
|
|
Direct X
12
Direct 3D
12_3
|
Direct X
12
Direct 3D
12_0
|
|
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
|
OpenGL
4.6
OpenCL
2.1
Vulkan
1.3
|
|
Shader Model
6.6
CUDA
8.9
-
-
PureVideo HD
VP12
VDPAU
Feature Set L
|
Shader Model
6.7
-
-
GFX
8
-
-
-
-
|
|
-
-
-
2x Fans
|
-
-
-
1x Fan
|
|
Power Connectors
-
-
-
-
-
-
1x 16-Pin 12VHPWR
|
-
-
-
-
-
-
-
-
|
|
Slots Required
3.0
PCIe Version
4.0
PCIe Lanes
16
|
Slots Required
2.0
PCIe Version
3.0
PCIe Lanes
8
|
|
-
-
-
-
|
Multi GPU Support
Supported
Type
CrossFire XDMA
|
|
Height
137 mm (5.39 in)
Width
304 mm (11.97 in)
Depth
61 mm (2.4 in)
|
Height
110 mm (4.33 in)
Width
145 mm (5.71 in)
Depth
37 mm (1.46 in)
|
Copy Link