AMD Instinct MI300P vs NVIDIA L4
AMD Instinct MI300P
NVIDIA L4
|
9728 Shaders
64GB HBM3
2100MHz
|
7680 Shaders
24GB GDDR6
2040MHz
|
|
Peak AI Performance
2.61 POPS
INT4 Tensor Sparse
|
Peak AI Performance
1 POPS
INT4 Tensor Sparse
|
|
FP32
81.72 TFLOPS
|
FP32
31.33 TFLOPS
|
|
FP16
81.72 TFLOPS
|
FP16
31.33 TFLOPS
|
|
Form Factor
OAM Module
-
|
Form Factor
PCIe Card
1.0-Slots
|
|
TDP
300W
|
TDP
72W
|
|
-
-
-
-
-
|
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%
|
|
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
2.61 POPS
INT4 Tensor Sparse
|
Peak AI
Performance
1 POPS
INT4 Tensor Sparse
|
|
-
-
-
|
-
-
-
|
|
FP8
-
1.31 PFLOPS
Tensor (FP16 Accumulate)
2.61 PFLOPS
Tensor (FP16 Accumulate) Sparse
1.31 PFLOPS
Tensor (FP32 Accumulate)
2.61 PFLOPS
Tensor (FP32 Accumulate) Sparse
|
FP8
-
250.68 TFLOPS
Tensor (FP16 Accumulate)
501.35 TFLOPS
Tensor (FP16 Accumulate) Sparse
250.68 TFLOPS
Tensor (FP32 Accumulate)
501.35 TFLOPS
Tensor (FP32 Accumulate) Sparse
|
|
FP16
81.72 TFLOPS
653.72 TFLOPS
Tensor (FP16 Accumulate)
1.31 PFLOPS
Tensor (FP16 Accumulate) Sparse
653.72 TFLOPS
Tensor (FP32 Accumulate)
1.31 PFLOPS
Tensor (FP32 Accumulate) Sparse
|
FP16
31.33 TFLOPS
125.34 TFLOPS
Tensor (FP16 Accumulate)
250.68 TFLOPS
Tensor (FP16 Accumulate) Sparse
125.34 TFLOPS
Tensor (FP32 Accumulate)
250.68 TFLOPS
Tensor (FP32 Accumulate) Sparse
|
|
FP32
81.72 TFLOPS
81.72 TFLOPS
Tensor
163.43 TFLOPS
Tensor Sparse
|
FP32
31.33 TFLOPS
-
-
|
|
FP64
40.86 TFLOPS
81.72 TFLOPS
Tensor
|
FP64
490 GFLOPS
-
|
|
BF16
-
653.72 TFLOPS
Tensor
1.31 PFLOPS
Tensor Sparse
|
BF16
31.33 TFLOPS
125.34 TFLOPS
Tensor
250.68 TFLOPS
Tensor Sparse
|
|
TF32
326.86 TFLOPS
Tensor
653.72 TFLOPS
Tensor Sparse
|
TF32
62.67 TFLOPS
Tensor
125.34 TFLOPS
Tensor Sparse
|
|
INT4
1.31 POPS
Tensor
2.61 POPS
Tensor Sparse
|
INT4
501.35 TOPS
Tensor
1 POPS
Tensor Sparse
|
|
INT8
-
1.31 POPS
Tensor
2.61 POPS
Tensor Sparse
|
INT8
-
250.68 TOPS
Tensor
501.35 TOPS
Tensor Sparse
|
|
-
-
|
INT32
15.67 TOPS
|
|
-
-
|
Ray Tracing
72.4 TOPS
|
|
Pixel
Fillrate
-
|
Pixel
Fillrate
163.2 GPixel/s
|
|
-
-
|
-
-
|
|
Texture
Fillrate
1276.8 GTexel/s
|
Texture
Fillrate
489.6 GTexel/s
|
|
Manufacturer
AMD
|
Manufacturer
NVIDIA
|
|
Chip Designer
AMD
|
Chip Designer
NVIDIA
|
|
Architecture
CDNA 3
|
Architecture
Ada Lovelace
|
|
Family
Instinct
|
Family
Server
|
|
Codename
Aqua Vanjaram
Aqua Vanjaram XL
Variant
Aqua Vanjaram XL
|
Codename
NV184
AD104
-
-
|
|
Market Segment
Server
|
Market Segment
Server
|
|
Release Date
12/6/2023
|
Release Date
3/21/2023
|
|
Foundry
TSMC
TSMC Active Interposer Die
|
Foundry
TSMC
-
|
|
Fabrication Node
N5
N6 Active Interposer Die
|
Fabrication Node
4N
-
|
|
Die Size
2x 370 mm²
-
|
Die Size
295 mm²
-
|
|
Transistor Count
2x 36.5 Billion
-
|
Transistor Count
35.8 Billion
-
|
|
Transistor Density
98.65M/mm²
-
|
Transistor Density
121.56M/mm²
-
|
|
Form
OAM Module
|
Form
PCIe Card
|
|
Shading Units
9728 Shaders
-
|
Shading Units
7680 Shaders
-
|
|
Texture Mapping Units
608 TMUs
|
Texture Mapping Units
240 TMUs
|
|
Render Output Units
-
|
Render Output Units
80 ROPs
|
|
Tensor Cores
608 T-Cores
|
Tensor Cores
240 T-Cores
|
|
-
-
|
Ray-Tracing Cores
60 RT-Cores
|
|
-
-
|
Streaming Multiprocessors
60 SMs
|
|
Compute Units
152 CUs
|
-
-
|
|
-
-
|
-
-
|
|
-
-
|
Graphics Processing Clusters
5 GPCs
|
|
-
-
1000MHz Base
2100MHz
|
-
-
795MHz Base
2040MHz
|
|
-
-
|
-
-
|
|
L1
-
-
16KB/CU
-
|
L1
64KB/SM Tex
128KB/SM
-
-
|
|
L2
16MB Shared
|
L2
48MB Shared
|
|
L3
128MB Shared
-
|
-
-
-
|
|
64GB
HBM3
ECC
|
24GB
GDDR6
-
|
|
Bus Width
4096Bit
|
Bus Width
192Bit
|
|
Clock
2600MHz
Transfer Rate
5.2GT/s
Bandwidth
2662.4GB/s
|
Clock
1563MHz
Transfer Rate
12.5GT/s
Bandwidth
300.1GB/s
|
|
-
-
-
-
-
-
-
-
-
|
-
-
-
-
-
-
-
-
-
|
|
TDP
300W
|
TDP
72W
|
|
-
-
|
-
-
|
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
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
2x VCN 2.6
|
Model
2x NVENC 8
|
|
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
|
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
|
|
No Decoders
|
Model
NVDEC 5
|
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
|
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
|
|
-
-
-
-
|
Direct X
12
Direct 3D
12_3
|
|
-
-
OpenCL
3.0
-
-
|
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
|
|
-
-
-
-
GFX
9.4
-
-
-
-
|
Shader Model
6.7
CUDA
8.9
-
-
PureVideo HD
VP12
VDPAU
Feature Set L
|
|
-
-
-
-
|
-
-
-
-
|
|
-
-
-
-
-
-
-
-
|
Power Connectors
-
-
-
-
-
-
1x 16-Pin 12VHPWR
|
|
-
-
PCIe Version
5.0
PCIe Lanes
16
|
Slots Required
1.0
PCIe Version
4.0
PCIe Lanes
16
|
|
Multi GPU Support
Supported
Type
Infinity Fabric
|
-
-
-
-
|
|
-
-
-
-
-
-
|
Height
56 mm (2.2 in)
Width
169 mm (6.65 in)
Depth
20 mm (0.79 in)
|
Copy Link