NVIDIA T4 vs AMD Radeon Instinct MI8
NVIDIA T4
AMD Radeon Instinct MI8
|
2560 Shaders
16GB GDDR6
1590MHz
|
4096 Shaders
4GB HBM
1000MHz
|
|
Peak Performance
260.51 TOPS
INT4 Tensor
|
Peak Performance
8.19 TFLOPS
FP32
|
|
FP32
8.14 TFLOPS
|
FP32
8.19 TFLOPS
|
|
FP16
16.28 TFLOPS
|
-
-
|
|
Form Factor
PCIe Card
1.0-Slots
|
Form Factor
PCIe Card
2.0-Slots
|
|
TDP
70W
|
TDP
175W
|
|
-
-
-
-
-
|
Power Connectors
-
1x 8-Pin
-
-
|
|
GB6 OpenCL N/A
0%
|
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%
|
|
Manufacturer
NVIDIA
|
Manufacturer
AMD
|
|
Chip Designer
NVIDIA
|
Chip Designer
AMD
|
|
Architecture
Turing
|
Architecture
GCN 3
|
|
Family
Server
|
Family
Instinct
|
|
Codename
NV164
TU104
Variant
TU104-895-A1
|
Codename
Fiji
-
Variant
Fiji XT GL
|
|
Market Segment
Server
|
Market Segment
Server
|
|
Release Date
9/13/2018
|
Release Date
6/20/2017
|
|
Foundry
TSMC
-
|
Foundry
TSMC
-
|
|
Fabrication Node
12FFN
-
|
Fabrication Node
28nm
-
|
|
Die Size
545 mm²
-
|
Die Size
596 mm²
-
|
|
Transistor Count
13.6 Billion
-
|
Transistor Count
8.9 Billion
-
|
|
Transistor Density
24.95M/mm²
-
|
Transistor Density
14.93M/mm²
-
|
|
Form
PCIe Card
|
Form
PCIe Card
|
|
Shading Units
2560 Shaders
-
|
Shading Units
4096 Shaders
-
|
|
Texture Mapping Units
160 TMUs
|
Texture Mapping Units
256 TMUs
|
|
Render Output Units
64 ROPs
|
Render Output Units
64 ROPs
|
|
Tensor Cores
320 T-Cores
|
-
-
|
|
Ray-Tracing Cores
40 RT-Cores
|
-
-
|
|
Streaming Multiprocessors
40 SMs
|
-
-
|
|
-
-
|
Compute Units
64 CUs
|
|
-
-
|
-
-
|
|
-
-
|
-
-
|
|
-
-
585MHz Base
1590MHz
|
-
-
1000MHz Base
1000MHz
|
|
Peak Performance
260.51 TOPS
INT4 Tensor
|
Peak Performance
8.19 TFLOPS
FP32
|
|
-
-
-
|
-
-
-
|
|
-
-
-
-
-
-
|
-
-
-
-
-
-
|
|
FP16
16.28 TFLOPS
65.13 TFLOPS Tensor (FP16 Accumulate)
-
65.13 TFLOPS Tensor (FP32 Accumulate)
-
|
-
-
-
-
-
-
|
|
FP32
8.14 TFLOPS
-
-
|
FP32
8.19 TFLOPS
-
-
|
|
FP64
0.25 TFLOPS
-
|
FP64
0.51 TFLOPS
-
|
|
-
-
-
-
|
-
-
-
-
|
|
-
-
-
|
-
-
-
|
|
INT4
260.51 TOPS Tensor
-
|
-
-
-
|
|
INT8
-
130.25 TOPS Tensor
-
|
-
-
-
-
|
|
-
-
|
-
-
|
|
Ray Tracing
31.8 TOPS
|
-
-
|
|
Pixel Fillrate
101.76 GPixel/s
|
Pixel Fillrate
64 GPixel/s
|
|
-
-
|
-
-
|
|
Texture Fillrate
254.4 GTexel/s
|
Texture Fillrate
256 GTexel/s
|
|
-
-
|
-
-
|
|
L1
32KB/SM Tex
64KB/SM
-
-
|
L1
-
-
16KB/CU
-
|
|
L2
4MB Shared
|
L2
2MB Shared
|
|
-
-
-
|
-
-
-
|
|
16GB
GDDR6
-
|
4GB
HBM
ECC
|
|
Bus Width
256Bit
|
Bus Width
4096Bit
|
|
Clock
625MHz
Transfer Rate
5GT/s
Bandwidth
160GB/s
|
Clock
500MHz
Transfer Rate
1GT/s
Bandwidth
512GB/s
|
|
-
-
-
-
-
-
-
-
-
|
-
-
-
-
-
-
-
-
-
|
|
TDP
70W
|
TDP
175W
|
|
-
-
|
-
-
|
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
|
|
Max Resolution
Unknown
|
Max Resolution
4096x2160
|
|
Max Resolution Refresh Rate
-
|
Max Resolution Refresh Rate
60Hz
|
|
Variable Refresh Rate
G-Sync
FreeSync
-
|
Variable Refresh Rate
-
FreeSync
-
|
|
Display Stream Compression (DSC)
Not Supported
|
Display Stream Compression (DSC)
Not Supported
|
|
Multi Monitor Support
Unknown
|
Multi Monitor Support
4
|
|
-
-
|
Content Protection
HDCP 1.4
|
|
Model
NVENC 7
|
Model
VCE 3.0
|
|
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
|
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
|
|
Model
NVDEC 4
|
Model
UVD 6.0
|
|
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
|
Codec
MPEG-1
MPEG-2
MPEG-4
JPEG
VC-1
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
|
|
Direct X
12
Direct 3D
12_2
|
Direct X
12
Direct 3D
12_0
|
|
OpenGL
4.6
OpenCL
3.0
Vulkan
1.2
|
OpenGL
4.6
OpenCL
2.1
Vulkan
1.2
|
|
Shader Model
6.6
CUDA
7.5
-
-
PureVideo HD
VP10
VDPAU
Feature Set J
|
Shader Model
6.5
-
-
GFX
8
-
-
-
-
|
|
-
-
-
-
|
-
-
-
-
|
|
-
-
-
-
-
-
-
-
|
Power Connectors
-
-
-
1x 8-Pin
-
-
-
|
|
Slots Required
1.0
PCIe Version
3.0
PCIe Lanes
16
|
Slots Required
2.0
PCIe Version
3.0
PCIe Lanes
16
|
|
Multi GPU Support
Supported
Type
NVLink
|
Multi GPU Support
Supported
Type
CrossFire XDMA
|
|
Height
69 mm (2.72 in)
Width
168 mm (6.61 in)
Depth
20 mm (0.79 in)
|
Height
111 mm (4.37 in)
Width
152 mm (5.98 in)
Depth
37 mm (1.46 in)
|
Copy Link