Radeon Pro Duo and Tesla M10 - video card comparison
Passmark - benchmark score Radeon Pro Duo vs Tesla M10
Radeon Pro Duo
8409
Tesla M10
3266
Radeon Pro Duo
Tesla M10
Architecture
GCN 3.0 (2014−2017)
Maxwell (2014−2018)
GPU code name
Capsaicin
GM107
Market segment
Workstation
Workstation
Release date
April 2016
May 2016
Bus support
PCIe 3.0
-
Interface
PCIe 3.0 x16
PCIe 3.0 x16
Supplementary power connectors
3x 8-pin
1x 8-pin
Boost clock speed
1000 MHz
1306 MHz
Compute units
128
-
Core clock speed
-
1033 MHz
Floating-point performance
2x 8,192 gflops
4x 1,672 gflops
Manufacturing process technology
28 nm
28 nm
Number of transistors
8,900 million
1,870 million
Pipelines / CUDA cores
4096
640
Power consumption (TDP)
350 Watt
225 Watt
Texture fill rate
256.0
52.24
Memory type
High Bandwidth Memory (HBM)
GDDR5
Maximum RAM amount
8 GB
8 GB
Memory bus width
4096 Bit
128 Bit
Memory clock speed
500 MHz
5200 MHz
Memory bandwidth
512 GB/s
83.2 GB/s
Display Connectors
1x HDMI, 3x DisplayPort
No outputs
Eyefinity
1
-
Number of Eyefinity displays
6
-
HDMI
+
-
DisplayPort support
+
-
DirectX
DirectX® 12
12 (11_0)
CUDA
-
5.0
Mantle
+
-
OpenCL
2.0
1.2
OpenGL
4.5
4.6
Shader Model
6.0
5.1
Vulkan
+
1.1.126
AppAcceleration
+
-
CrossFire
1
-
Enduro
+
-
FreeSync
1
-
FRTC
1
-
HD3D
+
-
LiquidVR
1
-
PowerTune
+
-
TressFX
1
-
TrueAudio
+
-
UVD
+
-
VCE
+
-
ZeroCore
+
-