Radeon Pro Duo and GeForce GTX 1070 - video card comparison
Passmark - benchmark score Radeon Pro Duo vs GeForce GTX 1070
Radeon Pro Duo
8409
GeForce GTX 1070
13916
Radeon Pro Duo
GeForce GTX 1070
Architecture
GCN 3.0 (2014−2017)
Pascal (2016−2021)
GPU code name
Capsaicin
Pascal GP104
Market segment
Workstation
Desktop
Release date
April 2016
May 2016
Bus support
PCIe 3.0
PCIe 3.0
Interface
PCIe 3.0 x16
PCIe 3.0 x16
Recommended system power (PSU)
-
500 Watt
Supplementary power connectors
3x 8-pin
8-pin
SLI options
-
+
Boost clock speed
1000 MHz
1683 MHz
Compute units
128
-
Core clock speed
-
1506 MHz
CUDA cores
-
1920
Floating-point performance
2x 8,192 gflops
6,463 gflops
Manufacturing process technology
28 nm
16 nm
Number of transistors
8,900 million
7,200 million
Pipelines / CUDA cores
4096
1920
Power consumption (TDP)
350 Watt
150 Watt
Maximum GPU temperature
-
94 °C
Texture fill rate
256.0
202.0
Memory type
High Bandwidth Memory (HBM)
GDDR5
Maximum RAM amount
8 GB
8 GB
Memory bus width
4096 Bit
256 Bit
Memory clock speed
500 MHz
8 GB/s
Memory bandwidth
512 GB/s
256 GB/s
Shared memory
-
-
Display Connectors
1x HDMI, 3x DisplayPort
DP 1.42, HDMI 2.0b, Dual Link-DVI
Multi monitor support
-
+
Eyefinity
1
-
Number of Eyefinity displays
6
-
HDMI
+
+
DisplayPort support
+
-
G-SYNC support
-
+
DirectX
DirectX® 12
12 (12_1)
CUDA
-
+
Mantle
+
-
OpenCL
2.0
1.2
OpenGL
4.5
4.5
Shader Model
6.0
6.4
Vulkan
+
+
Ansel
-
+
AppAcceleration
+
-
CrossFire
1
-
Enduro
+
-
FreeSync
1
-
FRTC
1
-
GPU Boost
-
3.0
HD3D
+
-
LiquidVR
1
-
PowerTune
+
-
TressFX
1
-
TrueAudio
+
-
UVD
+
-
VCE
+
-
VR Ready
-
+
ZeroCore
+
-