NVIDIA Quadro M6000 Professional Graphics Card Announced – 12 GB VRAM and 7.0 TFlops of Compute Power

Hassan Mujtaba
Posted Mar 17, 2015
18Shares
Share Tweet Submit

The GTC 2015 conference also served as the platform where NVIDIA introduced their Quadro M6000 graphics card. NVIDIA not only announced the GeForce GTX Titan X but also announced their professional Quadro M6000 graphics card aimed towards professionals and content creators who demand high-performance and massive compute capabilities delivered by NVIDIA’s next generation Maxwell GM200 graphics core.

NVIDIA Quadro M6000 Delivers 7.0 TFlops of Compute To Professionals With GM200 GPU Core

The NVIDIA Quadro M6000 is a professional card but has visual and technical similarities to the GeForce GTX Titan X. In terms of specifications, we are once again looking at the GM200 core with conservative core and memory clocks but the card does pack more unlocked compute performance hence being a better product suited towards content creators.

When it comes to specifications, the Quadro M6000 isn’t a huge step away from the GeForce GTX Titan X. Both are twins with the only difference being the market they are aimed towards. The specifications of the Quadro M6000 include 3072 CUDA cores which is equivalent to the GeForce GTX 690 that featured dual-GK104 cores. Maxwell however leverages per core performance over Kepler by 1.5x hence delivering higher graphical capabilities. The GM200 core on the Quadro M6000 comes with 6 Graphics Processing Clusters, each of which consist of four SMM (Streaming Multiprocessors Units) which have 128 cores in each SMM block. The GM200-400-A1 chip which is the fully enabled version of the core has all 24 SMM Units enabled which result in 3072 CUDA Cores, 192 Texture Mapping Units and 96 Raster operation units. Compared to the 2 MB L2 cache on GeForce GTX 980, the Quadro M6000 features 3 MB of L2 cache and has 6 64-bit memory controllers which result in a 384-bit memory interface. The core clocks are maintained at 988 MHz at default frequency.

Talking about the memory itself, the Quadro M6000 has 12 GB GDDR5 VRAM, which is the same as the Quadro K6000 and comes clocked at the standard speed of 6.6 GHz. The card pumps out 317.4 GB/s bandwidth. The card features a 225W TDP and the overall power consumption is lower than the Quadro K6000 which also had a 225W TDP but power consumption at maximum load is higher compared to the M6000. Power is fed through a single 8-Pin connector and display outputs include the reference Maxwell configuration of DVI, HDMI and three display ports.

NVIDIA GeForce 375.70 WHQL Driver Released - Optimized for Infinite Warfare, Titanfall 2, Skyrim Remaster

Unlike previous Quadro cards such as the K6000 itself, the NVIDIA Quadro M6000 features only 1/32 the DP (Double Precision) performance due to lack of FP64 hardware available on the Maxwell core architecture that was speculated a while ago. Hence, the M6000 features just 0.2 TFlops of FP64 compute performance like the GeForce GTX Titan X which FP32 performance is rated at 7.0 TFlops.

NVIDIA has redesigned the Quadro cards and finally ditching the older cooler shroud design in favor of the NVIDIA’s NVTTM cooler design. The Quadro M6000 has the same cooler as the Titan X with the only difference being the color scheme and a few connector panel replacements for stereo and power inputs. The card comes with a neat Green and Black color scheme with a black colored heatsink and cooler shroud. It features two SLI connectors to allow 4-Way GPU use in the most professional workloads.NVIDIA Quadro M6000_1

NVIDIA Quadro M6000 GM200 GPU Specifications:

GPU Name NVIDIA Quadro M6000 NVIDIA Quadro K6000 NVIDIA Quadro K5000 NVIDIA Quadro K4000 AMD FirePro  W9100 AMD FirePro W8100 AMD FirePro W7100 AMD FirePro W5100
GPU Core GM200 GK110 GK104 GK106 Hawaii XT Hawaii Pro Tonga Pro Bonaire Pro
SMM/Compute Units 24 15 8 4 44 40 28 12
Core Count 3072 2880 1536 768 2816 2560 1792 768
Core Clock 988 MHz 900 MHz 700 MHz 811 MHz 930 MHz 824 MHz 950 MHz 930 MHz
ROPs/TMUs 96/192 48/240 32/128 24/64 64/176 64/160 32/112 16/56
FP32 Compute 7 TFlops 5.2 TFlops 2.15 TFlops 1.24 TFlops 5.24 TFlops 4.20 TFlops 2.87 TFlops 1.43 TFlops
VRAM 12 GB GDDR5 12 GB GDDR5 4 GB GDDR5 3 GB GDDR5 16 GB GDDR5 8 GB GDDR5 8 GB GDDR5 4 GB GDDR5
Memory Bus 384-Bit 384-Bit 256-Bit 192-Bit 512-Bit 512-Bit 256-Bit 128-Bit
Memory Bandwidth 317.4 GB/s 288 GB/s 173 GB/s 134 GB/s 320 GB/s 320 GB/s 160 GB/s 96 GB/s
Memory Clock 6.6 GHz 6.0 GHz 5.4 GHz 5.6 GHz 5.0 GHz 5.0 GHz 5.0 GHz 5,5 GHz
TDP 250W 225W 122W 80W 275W 220W 150W 75W
NVIDIA's Pascal GPUs Inspired DICE To Add Hyper Settings for Mirror's Edge Catalyst

Share Tweet Submit