AMD Instinct MI355X vs NVIDIA GB200

AMD Instinct MI355X
NVIDIA GB200
16384 Shaders
288GB HBM3e
2400MHz
2x 18944 Shaders
384GB (2x 192GB) HBM3e
2112MHz
Peak AI Performance
20.13 PFLOPS
FP4 Tensor Sparse
Peak AI Performance
40 PFLOPS
FP4 Tensor Sparse
FP32
157.29 TFLOPS
FP32
160.04 TFLOPS
FP16
157.29 TFLOPS
FP16
320.08 TFLOPS
Form Factor
OAM Module
-
Form Factor
Superchip
-
TDP
1400W
TDP
2700W
-
-
-
-
-
-
-
-
-
-
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
20.13 PFLOPS
FP4 Tensor Sparse
Peak AI Performance
40 PFLOPS
FP4 Tensor Sparse
FP4
10.07 PFLOPS Tensor
20.13 PFLOPS Tensor Sparse
FP4
20 PFLOPS Tensor
40 PFLOPS Tensor Sparse
FP8
-
5.03 PFLOPS Tensor (FP16 Accumulate)
10.07 PFLOPS Tensor (FP16 Accumulate) Sparse
5.03 PFLOPS Tensor (FP32 Accumulate)
10.07 PFLOPS Tensor (FP32 Accumulate) Sparse
FP8
-
10 PFLOPS Tensor (FP16 Accumulate)
20 PFLOPS Tensor (FP16 Accumulate) Sparse
10 PFLOPS Tensor (FP32 Accumulate)
20 PFLOPS Tensor (FP32 Accumulate) Sparse
FP16
157.29 TFLOPS
2.52 PFLOPS Tensor (FP16 Accumulate)
5.03 PFLOPS Tensor (FP16 Accumulate) Sparse
2.52 PFLOPS Tensor (FP32 Accumulate)
5.03 PFLOPS Tensor (FP32 Accumulate) Sparse
FP16
320.08 TFLOPS
5 PFLOPS Tensor (FP16 Accumulate)
10 PFLOPS Tensor (FP16 Accumulate) Sparse
5 PFLOPS Tensor (FP32 Accumulate)
10 PFLOPS Tensor (FP32 Accumulate) Sparse
FP32
157.29 TFLOPS
157.29 TFLOPS Tensor
314.57 TFLOPS Tensor Sparse
FP32
160.04 TFLOPS
-
-
FP64
78.64 TFLOPS
78.64 TFLOPS Tensor
FP64
80.02 TFLOPS
78.13 TFLOPS Tensor
BF16
-
2.52 PFLOPS Tensor
5.03 PFLOPS Tensor Sparse
BF16
320.08 TFLOPS
5 PFLOPS Tensor
10 PFLOPS Tensor Sparse
-
-
-
TF32
2.5 PFLOPS Tensor
5 PFLOPS Tensor Sparse
INT4
5.03 POPS Tensor
10.07 POPS Tensor Sparse
-
-
-
INT8
-
5.03 POPS Tensor
10.07 POPS Tensor Sparse
INT8
-
10 POPS Tensor
20 POPS Tensor Sparse
-
-
INT32
160.04 TOPS
-
-
-
-
Pixel Fillrate
-
Pixel Fillrate
67.584 GPixel/s
-
-
-
-
Texture Fillrate
-
Texture Fillrate
1250.304 GTexel/s
Manufacturer
AMD
Manufacturer
NVIDIA
Chip Designer
AMD
Chip Designer
NVIDIA
Architecture
CDNA 4
Architecture
Blackwell
Family
Instinct
Family
Server
Codename
CDNA Next
-
-
-
Codename
NV190
GB100
Variant
Oberon
Market Segment
Server
Market Segment
Server
Release Date
6/12/2025
Release Date
3/18/2024
Foundry
TSMC
TSMC IO Die
Foundry
TSMC
-
Fabrication Node
N3P
N6 IO Die
Fabrication Node
4NP
-
Die Size
8x 181 mm²
-
Die Size
4x 810 mm²
-
Transistor Count
8x 17.4 Billion
2x 23 Billion IO Die
Transistor Count
4x 104 Billion
-
Transistor Density
96.13M/mm²
-
Transistor Density
128.40M/mm²
-
Form
OAM Module
Form
Superchip
Shading Units
16384 Shaders
-
Shading Units
2x 18944 Shaders
-
Texture Mapping Units
-
Texture Mapping Units
2x 592 TMUs
Render Output Units
-
Render Output Units
2x 32 ROPs
Tensor Cores
1024 T-Cores
Tensor Cores
2x 592 T-Cores
-
-
-
-
-
-
Streaming Multiprocessors
2x 148 SMs
Compute Units
256 CUs
-
-
-
-
-
-
-
-
-
-
-
-
-
2400MHz
2062MHz Tensor
-
-
2112MHz
-
-
-
-
L1
-
-
16KB/CU
-
L1
64KB/SM Tex
256KB/SM
-
-
L2
16MB Shared
L2
64MB Shared
L3
256MB Shared
-
-
-
-
288GB
HBM3e
ECC
384GB (2x 192GB)
HBM3e
-
Bus Width
8192Bit
Bus Width
8192Bit
Clock
3906MHz
Transfer Rate
7.8GT/s
Bandwidth
8000.1GB/s
Clock
3906MHz
Transfer Rate
7.8GT/s
Bandwidth
8000.1GB/s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
TDP
1400W
TDP
2700W
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
Max Resolution
Unknown
Max Resolution
Unknown
Max Resolution Refresh Rate
-
Max Resolution Refresh Rate
-
Variable Refresh Rate
-
-
-
Variable Refresh Rate
G-Sync
FreeSync
-
Display Stream Compression (DSC)
Not Supported
Display Stream Compression (DSC)
Not Supported
Multi Monitor Support
Unknown
Multi Monitor Support
Unknown
-
-
-
-
Model
4x VCN 4.0
No Encoders
-
Codec
-
-
-
-
-
-
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Model
4x VCN 4.0
Model
7x NVDEC 6
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
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
-
-
-
-
-
-
-
-
-
-
OpenCL
3.0
-
-
-
-
OpenCL
3.0
-
-
-
-
-
-
GFX
9.4
-
-
-
-
-
-
CUDA
10.0
-
-
PureVideo HD
VP13
VDPAU
Feature Set M
-
-
-
-
Not a Card
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
PCIe Version
5.0
PCIe Lanes
16
-
-
PCIe Version
6.0
PCIe Lanes
16
Multi GPU Support
Supported
Type
Infinity Fabric
Multi GPU Support
Supported
Type
NVLink
-
-
-
-
-
-
-
-
-
-
-
-
AMD Instinct MI355X AMD Instinct MI300X
AMD Instinct MI355X vs AMD Instinct MI300X
AMD Instinct MI355X AMD Instinct MI325X
AMD Instinct MI355X vs AMD Instinct MI325X
AMD Instinct MI355X AMD Instinct MI350X
AMD Instinct MI355X vs AMD Instinct MI350X
Change Comparison