2x Radeon Pro W6800X Duo vs NVIDIA RTX A6000
2x Radeon Pro W6800X Duo
$12,000
NVIDIA RTX A6000
$4,649
|
4x 3840 Shaders
128GB (4x 32GB) GDDR6
1970MHz
|
10752 Shaders
48GB GDDR6
1800MHz
|
|
Peak AI Performance
121.04 TFLOPS
FP16
|
Peak AI Performance
1.24 POPS
INT4 Tensor Sparse
|
|
FP32
60.52 TFLOPS
|
FP32
38.71 TFLOPS
|
|
FP16
121.04 TFLOPS
|
FP16
38.71 TFLOPS
|
|
Form Factor
MPX
2x 4.0-Slots
|
Form Factor
PCIe Card
2.0-Slots
|
|
TDP
800W
|
TDP
300W
|
|
-
-
-
-
-
|
Power Connectors
-
-
-
-
|
|
GB6 OpenCL N/A
0%
|
|
|
GB6 Metal N/A
0%
|
GB6 Metal N/A
0%
|
|
GB6 Vulkan N/A
0%
|
|
GB5 OpenCL 94,670
31%
|
GB5 OpenCL N/A
0%
|
|
GB5 CUDA N/A
0%
|
GB5 CUDA N/A
0%
|
|
GB5 Metal 129,470
72%
|
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 1,180
200%
|
OCT Metal N/A
0%
|
|
Peak AI
Performance
121.04 TFLOPS
FP16
|
Peak AI
Performance
1.24 POPS
INT4 Tensor Sparse
|
|
-
-
-
|
-
-
-
|
|
-
-
-
-
-
-
|
-
-
-
-
-
-
|
|
FP16
121.04 TFLOPS
-
-
-
-
|
FP16
38.71 TFLOPS
154.83 TFLOPS
Tensor (FP16 Accumulate)
309.66 TFLOPS
Tensor (FP16 Accumulate) Sparse
154.83 TFLOPS
Tensor (FP32 Accumulate)
309.66 TFLOPS
Tensor (FP32 Accumulate) Sparse
|
|
FP32
60.52 TFLOPS
-
-
|
FP32
38.71 TFLOPS
-
-
|
|
FP64
3.78 TFLOPS
-
|
FP64
610 GFLOPS
-
|
|
-
-
-
-
|
BF16
38.71 TFLOPS
154.83 TFLOPS
Tensor
309.66 TFLOPS
Tensor Sparse
|
|
-
-
-
|
TF32
77.41 TFLOPS
Tensor
154.83 TFLOPS
Tensor Sparse
|
|
-
-
-
|
INT4
619.32 TOPS
Tensor
1.24 POPS
Tensor Sparse
|
|
-
-
-
-
|
INT8
-
309.66 TOPS
Tensor
619.32 TOPS
Tensor Sparse
|
|
-
-
|
INT32
19.35 TOPS
|
|
-
-
|
Ray Tracing
75.6 TOPS
|
|
Pixel
Fillrate
189.12 GPixel/s
|
Pixel
Fillrate
201.6 GPixel/s
|
|
-
-
|
-
-
|
|
Texture
Fillrate
472.8 GTexel/s
|
Texture
Fillrate
604.8 GTexel/s
|
|
Manufacturer
Apple
|
Manufacturer
NVIDIA
|
|
Chip Designer
AMD
|
Chip Designer
NVIDIA
|
|
Architecture
RDNA 2
|
Architecture
Ampere
|
|
Family
Radeon Pro W
|
Family
RTX A
|
|
Codename
Sienna Cichlid
Navi 21
Variant
Navi 21 XLA
|
Codename
NV172
GA102
Variant
GA102-875-A1
|
|
Market Segment
Workstation
|
Market Segment
Workstation
|
|
Release Date
8/3/2021
|
Release Date
10/5/2020
|
|
Foundry
TSMC
-
|
Foundry
Samsung
-
|
|
Fabrication Node
N7
-
|
Fabrication Node
8N
-
|
|
Die Size
4x 520 mm²
-
|
Die Size
628 mm²
-
|
|
Transistor Count
4x 26.8 Billion
-
|
Transistor Count
28.3 Billion
-
|
|
Transistor Density
51.56M/mm²
-
|
Transistor Density
45.04M/mm²
-
|
|
Form
MPX
|
Form
PCIe Card
|
|
Shading Units
4x 3840 Shaders
-
|
Shading Units
10752 Shaders
-
|
|
Texture Mapping Units
4x 240 TMUs
|
Texture Mapping Units
336 TMUs
|
|
Render Output Units
4x 96 ROPs
|
Render Output Units
112 ROPs
|
|
-
-
|
Tensor Cores
336 T-Cores
|
|
Ray-Tracing Cores
4x 60 RT-Cores
|
Ray-Tracing Cores
84 RT-Cores
|
|
-
-
|
Streaming Multiprocessors
84 SMs
|
|
Compute Units
4x 60 CUs
|
-
-
|
|
-
-
|
-
-
|
|
Graphics Processing Clusters
4x 4 GPCs
|
-
-
|
|
-
-
1800MHz Base
1970MHz
|
-
-
1410MHz Base
1800MHz
|
|
L0
32KB/WGP
|
-
-
|
|
L1
-
-
-
128KB/Array
|
L1
64KB/SM Tex
128KB/SM
-
-
|
|
L2
4MB Shared
|
L2
6MB Shared
|
|
L3
128MB Shared
1.66TB/s
|
-
-
-
|
|
128GB (4x 32GB)
GDDR6
-
|
48GB
GDDR6
ECC
|
|
Bus Width
256Bit
|
Bus Width
384Bit
|
|
Clock
2000MHz
Transfer Rate
16GT/s
Bandwidth
512GB/s
|
Clock
2000MHz
Transfer Rate
16GT/s
Bandwidth
768GB/s
|
|
-
-
-
-
-
-
-
-
-
|
-
-
-
-
-
-
-
-
-
|
|
TDP
800W
|
TDP
300W
|
|
Temp
100°C Max
|
-
-
|
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
2x HDMI 2.0
-
-
8x Thunderbolt 3 (40Gbps)
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
4x DisplayPort 1.4
-
-
-
-
-
-
-
-
-
-
-
-
-
-
|
|
Max Resolution
6016x3384
|
Max Resolution
7680x4320
|
|
Max Resolution Refresh Rate
60Hz
|
Max Resolution Refresh Rate
60Hz
|
|
Variable Refresh Rate
-
FreeSync
-
|
Variable Refresh Rate
G-Sync
FreeSync
-
|
|
Display Stream Compression (DSC)
Supported
|
Display Stream Compression (DSC)
Supported
|
|
Multi Monitor Support
8
|
Multi Monitor Support
3
|
|
Content Protection
HDCP 2.3
|
Content Protection
HDCP 2.3
|
|
Model
VCN 3.0
|
Model
NVENC 7
|
|
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
|
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
|
|
Model
VCN 3.0
|
Model
2x NVDEC 5
|
|
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
-
-
|
|
Direct X
12
Direct 3D
12_2
|
Direct X
12
Direct 3D
12_2
|
|
OpenGL
4.6
OpenCL
2.1
Vulkan
1.2
|
OpenGL
4.6
OpenCL
3.0
Vulkan
1.2
|
|
Shader Model
6.5
-
-
GFX
10.3
-
-
-
-
|
Shader Model
6.6
CUDA
8.6
-
-
PureVideo HD
VP11
VDPAU
Feature Set K
|
|
-
-
-
-
|
-
-
-
1x Fan
|
|
-
-
-
-
-
-
-
-
|
Power Connectors
-
-
-
-
1x 8-Pin EPS
-
-
|
|
Slots Required
4.0
PCIe Version
4.0
PCIe Lanes
16
|
Slots Required
2.0
PCIe Version
4.0
PCIe Lanes
16
|
|
Multi GPU Support
Supported
Type
Infinity Fabric
|
Multi GPU Support
Supported
Type
2-way NVLink
|
|
-
-
-
-
-
-
|
Height
112 mm (4.41 in)
Width
267 mm (10.51 in)
Depth
40 mm (1.57 in)
|
Copy Link