NVIDIA L40

L40

XFX Radeon RX 6600 XT Speedster MERC 308

Radeon RX 6600 XT Speedster MERC 308

NVIDIA L40 vs XFX Radeon RX 6600 XT Speedster MERC 308 Full Specs

18,176 Shaders
2.49GHz
2,048 Shaders
2.61GHz
48GB GDDR6864GB/s
8GB GDDR6256GB/s
··
90.52 TFLOPS
··
10.68 TFLOPS
Form Factor
PCIe Card
Form Factor
PCIe Card
TDP
300W
TDP
160W
Power Connectors
1x 16-Pin 12VHPWR
-
Power Connectors
-
1x 8-Pin

L40L402.9 POPSINT4 Tensor Sparse
x135.63
Radeon RX 6600 XT Speedster MERC 308Radeon RX 6600 XT Speedster MERC 30821.36 TFLOPSFP16
x1

Clock Speed
···
Clock Speed
···
Peak OPS
2.9 POPSINT4 Tensor Sparse
Peak OPS
21.36 TFLOPSFP16
Tensor FP8-16
724.1 TFLOPS
FP8-16 Tensor Sparse
1.45 PFLOPS
Tensor FP8-32
362.1 TFLOPS
FP8-32 Tensor Sparse
724.1 TFLOPS
-
Tensor FP16-16
362.1 TFLOPS
FP16-16 Tensor Sparse
724.1 TFLOPS
Tensor FP16-32
181 TFLOPS
FP16-32 Tensor Sparse
362.1 TFLOPS
-
BF16
90.52 TFLOPS
Tensor BF16
181 TFLOPS
BF16 Tensor Sparse
362.1 TFLOPS
-
Tensor TF32
90.52 TFLOPS
Tensor TF32
-
FP32
90.52 TFLOPS
FP32
10.68 TFLOPS
FP64
1.41 TFLOPS
FP64
667.4 GFLOPS
Tensor INT4
1.45 POPS
Tensor INT4
-
Tensor INT8
724.1 TOPS
-
Ray
209.2 TOPS
Ray
-
Pixel Rate
478.1 GPixel/s
Pixel Rate
166.9 GPixel/s
Texture Rate
1.41 TTexel/s
Texture Rate
333.7 GTexel/s

Shaders
18,176 Shaders
Shaders
2,048 Shaders
TMUs
568 TMUs
TMUs
128 TMUs
ROPs
192 ROPs
ROPs
64 ROPs
Tensor Cores
568 T-Cores
Tensor Cores
-
RT Cores
142 RT-Cores
RT Cores
32 RT-Cores
SMs
142 SMs
CUs
32 CUs

Base Clock
735MHz
Base Clock
2.19GHz
Boost Clock
2.49GHz
Boost Clock
2.61GHz

L0 Cache
-
L0 Cache
32KB/WGP
L1
64KB/SM Tex
L1
128KB/Array
L2 Cache
96MB shared
L2 Cache
2MB shared
L3 Cache
-
L3 Cache
32MB shared
L3 Bandwidth
-
L3 Bandwidth
832GB/s

48GB GDDR6
8GB GDDR6
Memory Bus
384-bit
Memory Bus
128-bit
Memory Speed
18GT/s
Memory Speed
16GT/s
Memory Bandwidth
864GB/s
Memory Bandwidth
256GB/s
ECC
No
ECC
No

TDP
300W
TDP
160W
Max Temp
-
Max Temp
110°C Max

Max Resolution
7680x4320
Max Resolution
7680x4320
Refresh Rate Calculator
7680x4320
Resolution8K UHD
Refresh Rate
60Hz
Refresh Rate Calculator
7680x4320
Resolution8K UHD
Refresh Rate
120Hz
Multi-Monitor
4
Multi-Monitor
4
Adaptive Sync
G-Sync
FreeSync
Adaptive Sync
-
FreeSync
DSC
Supported
DSC
Supported
HDCP
HDCP 2.3
HDCP
HDCP 2.3

4x DisplayPort 1.4
-
3x DisplayPort 1.4
1x HDMI 2.1

Shader Model
6.6
Shader Model
6.5
DirectX
DirectX 12
Direct3D
12_3
DirectX
DirectX 12
Direct3D
12_2
OpenGL
4.6
OpenCL
3
Vulkan
1.3
OpenGL
4.6
OpenCL
2.1
Vulkan
1.2
CUDA
8.9
GFX
-
PureVideo HD
VP12
VDPAU
Feature Set L
CUDA
-
GFX
10.3
PureVideo HD
-
VDPAU
-

Encoder
2x NVENC 8
Encoder
VCN 3.0
Codec
AVC (H.264)
HEVC (H.265)
AV1
Codec
AVC (H.264)
HEVC (H.265)
-

Decoder
NVDEC 5
Decoder
VCN 3.0
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
-
VP9
AVC (H.264)
HEVC (H.265)
AV1

Form Factor
PCIe Card
Form Factor
PCIe Card
PCIe
PCIe 4.0 x16
2-Slots
PCIe
PCIe 4.0 x8
2.5-Slots
Height
111mm (4.37")
Width
267mm (10.51")
Depth
40mm (1.57")
Height
114mm (4.49")
Width
274mm (10.79")
Depth
50mm (1.97")
Cooling
Passive
-
Cooling
Open-Air
3x Fans
Power Connectors
1x 16-Pin 12VHPWR
Power Connectors
1x 8-Pin
Multi-GPU
-
Multi-GPU
Multi-GPU Support
Supported
Multi-GPU Type
Bridgeless

Manufacturer
Manufacturer
Chip Designer
Chip Designer
Architecture
Architecture
Family
Family
Branding
L40 branding
Branding
Radeon 2020 branding
Codename
NV182
Codename
Dimgrey Cavefish
Chip Variant
AD102-200-A1
Chip Variant
Navi 23 XL
Market Segment
Server
Market Segment
Desktop
Release Date
Oct 13, 2022
Release Date
Aug 11, 2021

Foundry
TSMC
Foundry
TSMC
Fabrication Node
4N
Fabrication Node
N7
Die Size
608mm²
Die Size
237mm²
Transistor Count
76.3B
Transistor Count
11.1B
Transistor Density
125.4 MTr/mm²
Transistor Density
46.67 MTr/mm²