AMD Instinct MI350X vs AMD Radeon Pro V320

AMD Instinct MI350X
AMD Radeon Pro V320
16384 Shaders
288GB HBM3e
2200MHz
4096 Shaders
8GB HBM2
1000MHz
Peak AI Performance
18.45 PFLOPS
FP4 Tensor Sparse
Peak AI Performance
16.38 TFLOPS
FP16
FP32
144.18 TFLOPS
FP32
8.19 TFLOPS
FP16
144.18 TFLOPS
FP16
16.38 TFLOPS
Form Factor
OAM Module
-
Form Factor
PCIe Card
2.0-Slots
TDP
1000W
TDP
230W
-
-
-
-
-
Power Connectors
-
2x 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%
Peak AI Performance
18.45 PFLOPS
FP4 Tensor Sparse
Peak AI Performance
16.38 TFLOPS
FP16
FP4
9.23 PFLOPS Tensor
18.45 PFLOPS Tensor Sparse
-
-
-
FP8
-
4.61 PFLOPS Tensor (FP16 Accumulate)
9.23 PFLOPS Tensor (FP16 Accumulate) Sparse
4.61 PFLOPS Tensor (FP32 Accumulate)
9.23 PFLOPS Tensor (FP32 Accumulate) Sparse
-
-
-
-
-
-
FP16
144.18 TFLOPS
2.31 PFLOPS Tensor (FP16 Accumulate)
4.61 PFLOPS Tensor (FP16 Accumulate) Sparse
2.31 PFLOPS Tensor (FP32 Accumulate)
4.61 PFLOPS Tensor (FP32 Accumulate) Sparse
FP16
16.38 TFLOPS
-
-
-
-
FP32
144.18 TFLOPS
144.18 TFLOPS Tensor
288.36 TFLOPS Tensor Sparse
FP32
8.19 TFLOPS
-
-
FP64
72.09 TFLOPS
72.09 TFLOPS Tensor
FP64
510 GFLOPS
-
BF16
-
2.31 PFLOPS Tensor
4.61 PFLOPS Tensor Sparse
-
-
-
-
-
-
-
-
-
-
INT4
4.61 POPS Tensor
9.23 POPS Tensor Sparse
-
-
-
INT8
-
4.61 POPS Tensor
9.23 POPS Tensor Sparse
-
-
-
-
-
-
-
-
-
-
-
-
Pixel Fillrate
-
Pixel Fillrate
64 GPixel/s
-
-
-
-
Texture Fillrate
-
Texture Fillrate
256 GTexel/s
Manufacturer
AMD
Manufacturer
AMD
Chip Designer
AMD
Chip Designer
AMD
Architecture
CDNA 4
Architecture
GCN 5
Family
Instinct
Family
Radeon Pro V
Codename
CDNA Next
-
-
-
Codename
Greenland
Vega 10
Variant
Vega 10 XT GL
Market Segment
Server
Market Segment
Server
Release Date
6/12/2025
Release Date
6/29/2017
Foundry
TSMC
TSMC IO Die
Foundry
GlobalFoundries
-
Fabrication Node
N3P
N6 IO Die
Fabrication Node
14LPP
-
Die Size
8x 181 mm²
-
Die Size
486 mm²
-
Transistor Count
8x 17.4 Billion
2x 23 Billion IO Die
Transistor Count
12.5 Billion
-
Transistor Density
96.13M/mm²
-
Transistor Density
25.72M/mm²
-
Form
OAM Module
Form
PCIe Card
Shading Units
16384 Shaders
-
Shading Units
4096 Shaders
-
Texture Mapping Units
-
Texture Mapping Units
256 TMUs
Render Output Units
-
Render Output Units
64 ROPs
Tensor Cores
1024 T-Cores
-
-
-
-
-
-
-
-
-
-
Compute Units
256 CUs
Compute Units
64 CUs
-
-
-
-
-
-
-
-
-
-
-
2200MHz
-
-
852MHz Base
1000MHz
-
-
-
-
L1
-
-
16KB/CU
-
L1
-
-
16KB/CU
-
L2
16MB Shared
L2
4MB Shared
L3
256MB Shared
-
-
-
-
288GB
HBM3e
ECC
8GB
HBM2
-
Bus Width
8192Bit
Bus Width
2048Bit
Clock
3906MHz
Transfer Rate
7.8GT/s
Bandwidth
8000.1GB/s
Clock
945MHz
Transfer Rate
1.9GT/s
Bandwidth
483.8GB/s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
TDP
1000W
TDP
230W
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
4x mini-DisplayPort 1.4
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Max Resolution
Unknown
Max Resolution
7680x4320
Max Resolution Refresh Rate
-
Max Resolution Refresh Rate
60Hz
Variable Refresh Rate
-
-
-
Variable Refresh Rate
-
FreeSync
-
Display Stream Compression (DSC)
Not Supported
Display Stream Compression (DSC)
Not Supported
Multi Monitor Support
Unknown
Multi Monitor Support
3
-
-
Content Protection
HDCP 2.2
Model
4x VCN 4.0
Model
VCE 4.0
Codec
-
-
-
-
-
-
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
Model
4x VCN 4.0
Model
UVD 7.0
Codec
MPEG-1
MPEG-2
MPEG-4
JPEG
VC-1
-
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_1
-
-
OpenCL
3.0
-
-
OpenGL
4.6
OpenCL
2.1
Vulkan
1.3
-
-
-
-
GFX
9.4
-
-
-
-
Shader Model
6.7
-
-
GFX
9
-
-
-
-
-
-
-
-
-
-
-
1x Fan
-
-
-
-
-
-
-
-
Power Connectors
-
-
-
2x 8-Pin
-
-
-
-
-
PCIe Version
5.0
PCIe Lanes
16
Slots Required
2.0
PCIe Version
3.0
PCIe Lanes
16
Multi GPU Support
Supported
Type
Infinity Fabric
Multi GPU Support
Supported
Type
CrossFire XDMA
-
-
-
-
-
-
Height
111 mm (4.37 in)
Width
267 mm (10.51 in)
Depth
37 mm (1.46 in)
Change Comparison