Blog

News

NVIDIA RTX A6000 and NVIDIA A40 GPUs Released – Here’s What You Should Know

October 4, 2020
24 min read
NVIDIA-RTX-A6000-1.jpg

NVIDIA Extends Ampere with RTX A6000 & A40

RTX A6000 & A40 Announcement

Today, NVIDIA released two new GPUs utilizing the new Ampere architecture, the NVIDIA RTX A6000 for workstations and NVIDIA A40 for server/datacenter workloads. The new cards feature new RT Cores, new Tensor Cores, and more CUDA cores than previous generations. With 48GB DDR6 (expandable up to 96 when using 2x cards with NVLink) RTX A6000 is the new flagship GPU of the Quadro line, to take the place of the Turing Powered Quadro RTX 8000. The NVIDIA A40 has essentially the same specs, but with passive cooling, and intended for use in server environments.

NVIDIA RTX A6000 vs NVIDIA A40 vs Quadro RTX 8000

NVIDIA RTX A6000NVIDIA A40Quadro RTX 8000
CUDA Cores10752107524608
Tensor Cores336336576
Memory Clock16Gbps GDDR614.5Gbps GDDR614Gbps GDDR6
Memory Bus Width384-bit384-bit384-bit
VRAM48GB48GB48GB
ECCPartialPartialPartial
(DRAM)(DRAM)(DRAM)
Half Precision??32.6 TFLOPS
Single Precision??16.3 TFLOPS
Tensor Performance??130.5 TFLOPS
TDP300W300W295W
CoolingActivePassiveActive
NVLink1x NVLink Gen31x NVLink Gen31x NVLInk Gen2
NVLink Speed112.5GB/sec112.5GB/sec50GB/sec
GPUGA102GA102TU102
ArchitectureAmpereAmpereTuring
Manufacturing ProcessSamsung 8nmSamsung 8nmTSMC 12nm FFN

More About the RTX A6000 & A40

NVIDIA A40

Image of NVIDIA A40 – Source: NVIDIA

NVIDIA Ampere Architecture CUDA Cores

Double-speed processing for single-precision floating point (FP32) operations and improved power efficiency provide significant performance improvements for graphics and simulation workflows, such as complex 3D computer-aided design (CAD) and computer-aided engineering (CAE), on the desktop.

Second-Generation RT Cores

With up to 2X the throughput over the previous generation and the ability to concurrently run ray tracing with either shading or denoising capabilities, second-generation RT Cores deliver massive speedups for workloads like photorealistic rendering of movie content, architectural design evaluations, and virtual prototyping of product designs. This technology also speeds up the rendering of ray-traced motion blur for faster results with greater visual accuracy.

Third-Generation Tensor Cores

New Tensor Float 32 (TF32) precision provides up to 5X the training throughput over the previous generation to accelerate AI and data science model training without requiring any code changes. Hardware support for structural sparsity doubles the throughput for inferencing. Tensor Cores also bring AI to graphics with capabilities like DLSS, AI denoising, and enhanced editing for select applications.

Third-Generation NVIDIA NVLink®

Increased GPU-to-GPU interconnect bandwidth provides a single scalable memory to accelerate graphics and compute workloads and tackle larger datasets.


NVLink #rd Gen

PCI Express Gen 4

Support for PCI Express Gen 4 provides double the bandwidth of PCIe Gen 3, improving data-transfer speeds from CPU memory for data-intensive tasks like AI and data science.

Power Efficiency

Featuring a dual-slot, power efficient design, the RTX A6000 is up to 2X more power efficient than Turing GPUs and crafted to fit into a wide range of workstations from worldwide OEM vendors.

NVIDIA RTX A6000 Specs at a Glance

GPU Memory48 GB GDDR6 with error-correcting code (ECC)
Display Ports4x DisplayPort 1.4*
Max Power Consumption300 W
Graphics BusPCI Express Gen 4 x 16
Form Factor4.4” (H) x 10.5” (L) dual slot
ThermalActive
NVLink2-way low profile (2-slot and 3-slot bridges)
Connect 2 RTX A6000
vGPU Software SupportNVIDIA GRID®, NVIDIA Quadro® Virtual Data Center Workstation,
NVIDIA Virtual Compute Server
vGPU Profiles Supported1 GB, 2 GB, 3 GB, 4 GB, 6 GB, 8 GB, 12 GB, 16 GB, 24 GB, 48 GB
VR ReadyYes

NVIDIA A40 Specs at a Glance

GPU Memory48 GB GDDR6 with error-correcting code (ECC)
GPU Memory Bandwidth696 GB/s
InterconnectNVIDIA NVLink 112.5 GB/s (bidirectional) PCIe Gen4 16 GB/s
NVLink2-way low profile (2-slot)
Display Ports3x DisplayPort 1.4*
Max Power Consumption300 W
Form Factor4.4″ (H) x 10.5″ (L) Dual Slot
ThermalPassive
vGPU Software SupportNVIDIA GRID®, NVIDIA Quadro® Virtual Data Center Workstation, NVIDIA Virtual Compute Server
vGPU Profiles Supported1 GB, 2 GB, 3 GB, 4 GB, 6 GB, 8 GB, 12 GB, 16 GB, 24 GB, 48 GB
NVENC | NVDEC1x | 2x (includes AV1 decode)
Secure and Measured Boot with Hardware Root of TrustCEC 1712
NEBS ReadyLevel 3
Power Connector8-pin CPU

NVIDIA RTX A6000 and NVIDIA A40 Available in New Systems

Exxact will offer NVIDIA A6000 and A40 across a broad spectrum of Deep Learning Workstations & Servers, Data Science Workstations, NVIDIA RTX Server, and other Ampere and NVIDIA Quadro based systems.

Have any questions about the new NVIDIA GPUs, or system availability?
Contact Exxact Today

Free Resources

Browse our whitepapers, e-books, case studies, and reference architecture.

Explore
NVIDIA-RTX-A6000-1.jpg
News

NVIDIA RTX A6000 and NVIDIA A40 GPUs Released – Here’s What You Should Know

October 4, 2020 24 min read

NVIDIA Extends Ampere with RTX A6000 & A40

RTX A6000 & A40 Announcement

Today, NVIDIA released two new GPUs utilizing the new Ampere architecture, the NVIDIA RTX A6000 for workstations and NVIDIA A40 for server/datacenter workloads. The new cards feature new RT Cores, new Tensor Cores, and more CUDA cores than previous generations. With 48GB DDR6 (expandable up to 96 when using 2x cards with NVLink) RTX A6000 is the new flagship GPU of the Quadro line, to take the place of the Turing Powered Quadro RTX 8000. The NVIDIA A40 has essentially the same specs, but with passive cooling, and intended for use in server environments.

NVIDIA RTX A6000 vs NVIDIA A40 vs Quadro RTX 8000

NVIDIA RTX A6000NVIDIA A40Quadro RTX 8000
CUDA Cores10752107524608
Tensor Cores336336576
Memory Clock16Gbps GDDR614.5Gbps GDDR614Gbps GDDR6
Memory Bus Width384-bit384-bit384-bit
VRAM48GB48GB48GB
ECCPartialPartialPartial
(DRAM)(DRAM)(DRAM)
Half Precision??32.6 TFLOPS
Single Precision??16.3 TFLOPS
Tensor Performance??130.5 TFLOPS
TDP300W300W295W
CoolingActivePassiveActive
NVLink1x NVLink Gen31x NVLink Gen31x NVLInk Gen2
NVLink Speed112.5GB/sec112.5GB/sec50GB/sec
GPUGA102GA102TU102
ArchitectureAmpereAmpereTuring
Manufacturing ProcessSamsung 8nmSamsung 8nmTSMC 12nm FFN

More About the RTX A6000 & A40

NVIDIA A40

Image of NVIDIA A40 – Source: NVIDIA

NVIDIA Ampere Architecture CUDA Cores

Double-speed processing for single-precision floating point (FP32) operations and improved power efficiency provide significant performance improvements for graphics and simulation workflows, such as complex 3D computer-aided design (CAD) and computer-aided engineering (CAE), on the desktop.

Second-Generation RT Cores

With up to 2X the throughput over the previous generation and the ability to concurrently run ray tracing with either shading or denoising capabilities, second-generation RT Cores deliver massive speedups for workloads like photorealistic rendering of movie content, architectural design evaluations, and virtual prototyping of product designs. This technology also speeds up the rendering of ray-traced motion blur for faster results with greater visual accuracy.

Third-Generation Tensor Cores

New Tensor Float 32 (TF32) precision provides up to 5X the training throughput over the previous generation to accelerate AI and data science model training without requiring any code changes. Hardware support for structural sparsity doubles the throughput for inferencing. Tensor Cores also bring AI to graphics with capabilities like DLSS, AI denoising, and enhanced editing for select applications.

Third-Generation NVIDIA NVLink®

Increased GPU-to-GPU interconnect bandwidth provides a single scalable memory to accelerate graphics and compute workloads and tackle larger datasets.


NVLink #rd Gen

PCI Express Gen 4

Support for PCI Express Gen 4 provides double the bandwidth of PCIe Gen 3, improving data-transfer speeds from CPU memory for data-intensive tasks like AI and data science.

Power Efficiency

Featuring a dual-slot, power efficient design, the RTX A6000 is up to 2X more power efficient than Turing GPUs and crafted to fit into a wide range of workstations from worldwide OEM vendors.

NVIDIA RTX A6000 Specs at a Glance

GPU Memory48 GB GDDR6 with error-correcting code (ECC)
Display Ports4x DisplayPort 1.4*
Max Power Consumption300 W
Graphics BusPCI Express Gen 4 x 16
Form Factor4.4” (H) x 10.5” (L) dual slot
ThermalActive
NVLink2-way low profile (2-slot and 3-slot bridges)
Connect 2 RTX A6000
vGPU Software SupportNVIDIA GRID®, NVIDIA Quadro® Virtual Data Center Workstation,
NVIDIA Virtual Compute Server
vGPU Profiles Supported1 GB, 2 GB, 3 GB, 4 GB, 6 GB, 8 GB, 12 GB, 16 GB, 24 GB, 48 GB
VR ReadyYes

NVIDIA A40 Specs at a Glance

GPU Memory48 GB GDDR6 with error-correcting code (ECC)
GPU Memory Bandwidth696 GB/s
InterconnectNVIDIA NVLink 112.5 GB/s (bidirectional) PCIe Gen4 16 GB/s
NVLink2-way low profile (2-slot)
Display Ports3x DisplayPort 1.4*
Max Power Consumption300 W
Form Factor4.4″ (H) x 10.5″ (L) Dual Slot
ThermalPassive
vGPU Software SupportNVIDIA GRID®, NVIDIA Quadro® Virtual Data Center Workstation, NVIDIA Virtual Compute Server
vGPU Profiles Supported1 GB, 2 GB, 3 GB, 4 GB, 6 GB, 8 GB, 12 GB, 16 GB, 24 GB, 48 GB
NVENC | NVDEC1x | 2x (includes AV1 decode)
Secure and Measured Boot with Hardware Root of TrustCEC 1712
NEBS ReadyLevel 3
Power Connector8-pin CPU

NVIDIA RTX A6000 and NVIDIA A40 Available in New Systems

Exxact will offer NVIDIA A6000 and A40 across a broad spectrum of Deep Learning Workstations & Servers, Data Science Workstations, NVIDIA RTX Server, and other Ampere and NVIDIA Quadro based systems.

Have any questions about the new NVIDIA GPUs, or system availability?
Contact Exxact Today

Free Resources

Browse our whitepapers, e-books, case studies, and reference architecture.

Explore