
Pascal is the codename for a
GPU
A graphics processing unit (GPU) is a specialized electronic circuit designed for digital image processing and to accelerate computer graphics, being present either as a discrete video card or embedded on motherboards, mobile phones, personal ...
microarchitecture
In electronics, computer science and computer engineering, microarchitecture, also called computer organization and sometimes abbreviated as μarch or uarch, is the way a given instruction set architecture (ISA) is implemented in a particular ...
developed by
Nvidia
Nvidia Corporation ( ) is an American multinational corporation and technology company headquartered in Santa Clara, California, and incorporated in Delaware. Founded in 1993 by Jensen Huang (president and CEO), Chris Malachowsky, and Curti ...
, as the successor to the
Maxwell
Maxwell may refer to:
People
* Maxwell (surname), including a list of people and fictional characters with the name
** James Clerk Maxwell, mathematician and physicist
* Justice Maxwell (disambiguation)
* Maxwell baronets, in the Baronetage of N ...
architecture. The architecture was first introduced in April 2016 with the release of the Tesla P100 (GP100) on April 5, 2016, and is primarily used in the
GeForce 10 series
The GeForce 10 series is a series of graphics processing units developed by Nvidia, initially based on the Pascal microarchitecture announced in March 2014. This design series succeeded the GeForce 900 series, and is succeeded by the GeForce 1 ...
, starting with the GeForce GTX 1080 and GTX 1070 (both using the GP104 GPU), which were released on May 27, 2016, and June 10, 2016, respectively. Pascal was manufactured using
TSMC
Taiwan Semiconductor Manufacturing Company Limited (TSMC or Taiwan Semiconductor) is a Taiwanese multinational semiconductor contract manufacturing and design company. It is one of the world's most valuable semiconductor companies, the world' ...
's
16 nm
Sixteen or 16 may refer to:
*16 (number)
*one of the years 16 BC, AD 16, 1916, 2016
Films
* ''Pathinaaru'' or ''Sixteen'', a 2010 Tamil film
* ''Sixteen'' (1943 film), a 1943 Argentine film directed by Carlos Hugo Christensen
* ''Sixteen'' (2 ...
FinFET
A fin field-effect transistor (FinFET) is a multigate device, a MOSFET (metal–oxide–semiconductor field-effect transistor) built on a substrate where the gate is placed on two, three, or four sides of the channel or wrapped around the chann ...
process, and later
Samsung
Samsung Group (; stylised as SΛMSUNG) is a South Korean Multinational corporation, multinational manufacturing Conglomerate (company), conglomerate headquartered in the Samsung Town office complex in Seoul. The group consists of numerous a ...
's
14nm FinFET process.
The architecture is named after the 17th century French mathematician and physicist,
Blaise Pascal
Blaise Pascal (19June 162319August 1662) was a French mathematician, physicist, inventor, philosopher, and Catholic Church, Catholic writer.
Pascal was a child prodigy who was educated by his father, a tax collector in Rouen. His earliest ...
.
In April 2019, Nvidia enabled a software implementation of
DirectX Raytracing
DirectX Raytracing (DXR) is a feature introduced in Microsoft's DirectX 12 that implements Ray tracing (graphics), ray tracing, for video graphic rendering. DXR was released with the Windows 10 October update (version 1809) on October 10, 2018. I ...
on Pascal-based cards starting with the GTX 1060 6 GB, and in the
16 series cards, a feature reserved to the Turing-based RTX series up to that point.
Details
In March 2014, Nvidia announced that the successor to
Maxwell
Maxwell may refer to:
People
* Maxwell (surname), including a list of people and fictional characters with the name
** James Clerk Maxwell, mathematician and physicist
* Justice Maxwell (disambiguation)
* Maxwell baronets, in the Baronetage of N ...
would be the Pascal microarchitecture; announced on May 6, 2016, and released on May 27 of the same year. The Tesla P100 (GP100 chip) has a different version of the Pascal architecture compared to the GTX GPUs (GP104 chip). The
shader units in GP104 have a
Maxwell
Maxwell may refer to:
People
* Maxwell (surname), including a list of people and fictional characters with the name
** James Clerk Maxwell, mathematician and physicist
* Justice Maxwell (disambiguation)
* Maxwell baronets, in the Baronetage of N ...
-like design.
Architectural improvements of the GP100 architecture include the following:
* In Pascal, a SM (streaming multiprocessor) consists of between 64-128 CUDA cores, depending on if it is GP100 or GP104.
Maxwell
Maxwell may refer to:
People
* Maxwell (surname), including a list of people and fictional characters with the name
** James Clerk Maxwell, mathematician and physicist
* Justice Maxwell (disambiguation)
* Maxwell baronets, in the Baronetage of N ...
contained 128 CUDA cores per SM; Kepler had 192, Fermi 32 and Tesla 8. The GP100 SM is partitioned into two processing blocks, each having 32 single-precision CUDA cores, an instruction buffer, a warp scheduler, 2 texture mapping units and 2 dispatch units.
*
CUDA
In computing, CUDA (Compute Unified Device Architecture) is a proprietary parallel computing platform and application programming interface (API) that allows software to use certain types of graphics processing units (GPUs) for accelerated gene ...
Compute Capability 6.0.
*
High Bandwidth Memory
High Bandwidth Memory (HBM) is a computer memory interface for 3D-stacked synchronous dynamic random-access memory (SDRAM) initially from Samsung, AMD and SK Hynix. It is used in conjunction with high-performance graphics accelerators, network ...
2 — some cards feature 16 GiB HBM2 in four stacks with a total bus width of 4096 bits and a memory bandwidth of 720 GB/s.
* Unified memory — a memory architecture where the CPU and GPU can access both main system memory and memory on the graphics card with the help of a technology called "Page Migration Engine".
*
NVLink
NVLink is a wire-based serial multi-lane near-range communications protocol, communications link developed by Nvidia. Unlike PCI Express, a device can consist of multiple NVLinks, and devices use mesh networking to communicate instead of a central ...
— a high-bandwidth bus between the CPU and GPU, and between multiple GPUs. Allows much higher transfer speeds than those achievable by using PCI Express; estimated to provide between 80 and 200 GB/s.
* 16-bit (
FP16
In computing, half precision (sometimes called FP16 or float16) is a binary floating-point computer number format that occupies 16 bits (two bytes in modern computers) in computer memory. It is intended for storage of floating-point values in a ...
) floating-point operations (colloquially "half precision") can be executed at twice the rate of 32-bit floating-point operations ("single precision") and 64-bit floating-point operations (colloquially "double precision") executed at half the rate of 32-bit floating point operations.
* More registers — twice the amount of registers per CUDA core compared to Maxwell.
* More shared memory.
* Dynamic load balancing scheduling system.
This allows the scheduler to dynamically adjust the amount of the GPU assigned to multiple tasks, ensuring that the GPU remains saturated with work except when there is no more work that can safely be distributed to distribute.
[ Nvidia therefore has safely enabled asynchronous compute in Pascal's driver.][
* Instruction-level and thread-level preemption.]
Architectural improvements of the GP104 architecture include the following:[
* CUDA Compute Capability 6.1.
* ]GDDR5X
Graphics Double Data Rate 5 Synchronous Dynamic Random-Access Memory (GDDR5 SDRAM) is a type of synchronous graphics random-access memory (SGRAM) with a high bandwidth ("double data rate") interface designed for use in graphics cards, game con ...
— new memory standard supporting 10Gbit/s data rates, updated memory controller.
* Simultaneous Multi-Projection - generating multiple projections of a single geometry stream, as it enters the SMP engine from upstream shader stages.
* DisplayPort
DisplayPort (DP) is a digital interface used to connect a video source, such as a Personal computer, computer, to a display device like a Computer monitor, monitor. Developed by the Video Electronics Standards Association (VESA), it can also car ...
1.4, HDMI
High-Definition Multimedia Interface (HDMI) is a proprietary digital interface used to transmit high-quality video and audio signals between devices. It is commonly used to connect devices such as televisions, computer monitors, projectors, gam ...
2.0b.
* Fourth generation Delta Color Compression.
* Enhanced SLI Interface — SLI interface with higher bandwidth compared to the previous versions.
* PureVideo Feature Set H hardware video decoding HEVC Main10 (10-bit), Main12 (12-bit) and VP9 hardware decoding.
* HDCP
High-bandwidth Digital Content Protection (HDCP) is a form of digital copy protection developed by Intel Corporation to prevent copying of digital audio and video content as it travels across connections. Types of connections include DisplayPort ...
2.2 support for 4K DRM protected content playback and streaming (Maxwell GM200 and GM204 lack HDCP 2.2 support, GM206 supports HDCP 2.2).
* NVENC
NVENC (short for Nvidia Encoder) is a feature in Nvidia graphics cards that performs Data compression, video encoding, offloading this compute-intensive task from the Central processing unit, CPU to a dedicated part of the Graphics processing uni ...
HEVC Main10 10bit hardware encoding.
* GPU Boost 3.0.
* Instruction-level preemption.[ In graphics tasks, the driver restricts preemption to the pixel-level, because pixel tasks typically finish quickly and the overhead costs of doing pixel-level preemption are lower than instruction-level preemption (which is expensive).][ Compute tasks get thread-level or instruction-level preemption,][ because they can take longer times to finish and there are no guarantees on when a compute task finishes. Therefore the driver enables the expensive instruction-level preemption for these tasks.][
]
Overview
Graphics Processor Cluster
A chip is partitioned into Graphics Processor Clusters (GPCs). For the GP104 chips, a GPC encompasses 5 SMs.
Streaming Multiprocessor "Pascal"
A "Streaming Multiprocessor" is analogous to AMD's Compute Unit
A graphics processing unit (GPU) is a specialized electronic circuit designed for digital image processing and to accelerate computer graphics, being present either as a discrete video card or embedded on motherboards, mobile phones, personal co ...
. An SM encompasses 128 single-precision ALUs ("CUDA cores") on GP104 chips and 64 single-precision ALUs on GP100 chips. While all CU versions consist of 64 shader processors (i.e. 4 SIMD Vector Units, each 16 lanes wide), Nvidia experimented with very different numbers of CUDA cores:
* On Tesla, 1 SM combines 8 single-precision (FP32) shader processors
* On Fermi, 1 SM combines 32 single-precision (FP32) shader processors
* On Kepler
Johannes Kepler (27 December 1571 – 15 November 1630) was a German astronomer, mathematician, astrologer, natural philosopher and writer on music. He is a key figure in the 17th-century Scientific Revolution, best known for his laws of p ...
, 1 SM combines 192 single-precision (FP32) shader processors and 64 double-precision (FP64) units (on GK110 GPUs)
* On Maxwell
Maxwell may refer to:
People
* Maxwell (surname), including a list of people and fictional characters with the name
** James Clerk Maxwell, mathematician and physicist
* Justice Maxwell (disambiguation)
* Maxwell baronets, in the Baronetage of N ...
, 1 SM combines 128 single-precision (FP32) shader processors
* On Pascal, it depends:
** On GP100, 1 SM combines 64 single-precision (FP32) shader processors and also 32 double-precision (FP64) providing a 2:1 ratio of single- to double-precision throughput. The GP100 uses more flexible FP32 cores that are able to process one single-precision or two half-precision numbers in a two-element vector. This is intended to better serve machine learning
Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of Computational statistics, statistical algorithms that can learn from data and generalise to unseen data, and thus perform Task ( ...
tasks.
** On GP104, 1 SM combines 128 single-precision ALUs, 4 double-precision ALUs (providing a 32:1 ratio), and one half-precision ALU which contains a vector of two half-precision floats which can execute the same instruction on both floats, providing a 64:1 ratio if the same instruction is used on both elements.
Polymorph-Engine 4.0
The Polymorph Engine version 4.0 is the unit responsible for Tessellation
A tessellation or tiling is the covering of a surface, often a plane, using one or more geometric shapes, called ''tiles'', with no overlaps and no gaps. In mathematics, tessellation can be generalized to higher dimensions and a variety ...
. It corresponds functionally with AMD's Geometric Processor. It has been moved from the shader module to the TPC to allow one Polymorph engine to feed multiple SMs within the TPC.
Chips
* GP100: Nvidia's Tesla P100 GPU accelerator is targeted at GPGPU
General-purpose computing on graphics processing units (GPGPU, or less often GPGP) is the use of a graphics processing unit (GPU), which typically handles computation only for computer graphics, to perform computation in applications traditiona ...
applications such as FP64 double precision compute and deep learning training that uses FP16. It uses HBM2 memory. Quadro GP100 also uses the GP100 GPU.
* GP102: This GPU is used in the Titan Xp, Titan X Pascal and the GeForce GTX 1080 Ti. It is also used in the Quadro P6000 & Tesla P40.
* GP104: This GPU is used in the GeForce GTX 1070, GTX 1070 Ti, GTX 1080, and some GTX 1060 6 GB's. The GTX 1070 has 15/20 and the GTX 1070 Ti has 19/20 of its SMs enabled; both utilize GDDR5 memory. The GTX 1080 is a fully unlocked chip and uses GDDR5X memory. Some GTX 1060 6 GB's use GP104 with 10/20 SMs enabled and GDDR5X memory. It is also used in the Quadro P5000, Quadro P4000, Quadro P3200 (mobile applications) and Tesla P4.
* GP106: This GPU is used in the GeForce GTX 1060 with GDDR5 memory. It is also used in the Quadro P2000.
* GP107: This GPU is used in the GeForce GTX 1050 and 1050 Ti. It is also used in the Quadro P1000, Quadro P600, Quadro P620 & Quadro P400.
* GP108: This GPU is used in the GeForce GT 1010 and GeForce GT 1030.
Performance
The theoretical single-precision processing power of a Pascal GPU in GFLOPS
Floating point operations per second (FLOPS, flops or flop/s) is a measure of computer performance in computing, useful in fields of scientific computations that require floating-point calculations.
For such cases, it is a more accurate measu ...
is computed as 2 × operations per FMA instruction per CUDA core per cycle × number of CUDA cores × core clock speed (in GHz).
The theoretical double-precision processing power of a Pascal GPU is 1/2 of the single precision performance on Nvidia GP100, and 1/32 of Nvidia GP102, GP104, GP106, GP107 & GP108.
The theoretical half-precision processing power of a Pascal GPU is 2× of the single precision performance on GP100[ and 1/64 on GP104, GP106, GP107 & GP108.][
]
Successor
The Pascal architecture was succeeded in 2017 by Volta in the HPC, cloud computing
Cloud computing is "a paradigm for enabling network access to a scalable and elastic pool of shareable physical or virtual resources with self-service provisioning and administration on-demand," according to International Organization for ...
, and self-driving car
A self-driving car, also known as an autonomous car (AC), driverless car, robotic car or robo-car, is a car that is capable of operating with reduced or no human input. They are sometimes called robotaxis, though this term refers specifica ...
markets, and in 2018 by Turing
Alan Mathison Turing (; 23 June 1912 – 7 June 1954) was an English mathematician, computer scientist, logician, cryptanalyst, philosopher and theoretical biologist. He was highly influential in the development of theoretical compute ...
in the consumer and business market.
P100 accelerator and DGX-1
See also
* List of eponyms of Nvidia GPU microarchitectures
* List of Nvidia graphics processing units
This list contains general information about graphics processing units (GPUs) and video cards from Nvidia, based on official specifications. In addition some Comparison of Nvidia nForce chipsets, Nvidia motherboards come with integrated onboard GP ...
* Nvidia NVDEC
* Nvidia NVENC
NVENC (short for Nvidia Encoder) is a feature in Nvidia graphics cards that performs video encoding, offloading this compute-intensive task from the CPU to a dedicated part of the GPU. It was introduced with the Kepler-based GeForce 600 series ...
References
{{Nvidia
Nvidia microarchitectures
Nvidia Pascal