GTC 2016 Europe: Breaking New Database Performance Records with GPUs

16
New performance benchmarks over 40 billion rows Bill Maimone, Head of Engineering -- MapD Mazhar Memon, CTO -- Bitfusion Jerry Gutierrez, Global HPC Sales Leader -- IBM Cloud

Transcript of GTC 2016 Europe: Breaking New Database Performance Records with GPUs

Page 1: GTC 2016 Europe: Breaking New Database Performance Records with GPUs

New performance benchmarks over 40 billion rowsBill Maimone, Head of Engineering -- MapDMazhar Memon, CTO -- BitfusionJerry Gutierrez, Global HPC Sales Leader -- IBM Cloud

Page 2: GTC 2016 Europe: Breaking New Database Performance Records with GPUs

2© 2016 IBM Corporation

IBM Cloud/SoftLayer Key Differentiators for GPU Accelerated Computing

Virtual/Bare Metal Servers with Hourly or Monthly Billing The Latest Intel CPUs and NVIDIA GPUs On-demand provisioning Triple-network architecture Private network only server deployments, private VLAN Un-metered private network Flash Based NetApp Performance/Endurance Storage Enterprise Grade Encryption

Page 3: GTC 2016 Europe: Breaking New Database Performance Records with GPUs

3© 2016 IBM Corporation

IBM Cloud -SoftLayerGlobal reach with local presence

Data centers near every major metro area enabling low-latency connectivity to cloud infrastructure.

Page 4: GTC 2016 Europe: Breaking New Database Performance Records with GPUs

4© 2016 IBM Corporation

Hourly GPU Servers Now Available!

Page 5: GTC 2016 Europe: Breaking New Database Performance Records with GPUs

MapD

• Analyzing increasingly massive datasets is critical• Ability to scale past a single node• Need access to the latest GPUs• Did not want to own or build infrastructure• Worked with IBM Cloud and very quickly came up

with a compelling solution

5

Page 6: GTC 2016 Europe: Breaking New Database Performance Records with GPUs

The data explosion is just beginning

6

Source: IDC and EMC Digital Universe

Report

Page 7: GTC 2016 Europe: Breaking New Database Performance Records with GPUs

Confidential & Proprietary

MapD

7

MapD Analytic DatabaseSQL-based column storeWritten ground-up for GPU

MapD ImmerseReact.js/d3 charts & dashboardsGPU rendering where it matters

https://www.mapd.com/blog/2016/06/27/crushing-the-billion-row-taxi-data-benchmark/

Page 8: GTC 2016 Europe: Breaking New Database Performance Records with GPUs

The Dataset & Queries

Confidential & Proprietary 8

1. Query Id is Q001 : query is 'select count(*) from flights2’2. Query Id is Q002 : query is 'select carrier_name, count(*)

from flights2 group by carrier_name’3. Query Id is Q003 : query is 'select carrier_name,

avg(arrdelay) from flights2 group by carrier_name'

US Flight Data from 1987 to 2008. Total dataset is 128M rows and was replicated 312 times.

Page 9: GTC 2016 Europe: Breaking New Database Performance Records with GPUs

9

Querying 40 billion rows in milliseconds.

Page 10: GTC 2016 Europe: Breaking New Database Performance Records with GPUs

Node

GPUGPUGPUGPU

GPU capacity limited by the node

Node

GPUGPUGPUGPU

Node

GPUGPUGPUGPU

Node

GPUGPUGPUGPU

Node

GPUGPUGPUGPU

Node

GPUGPUGPUGPU

Node

GPUGPUGPUGPU

Node

GPUGPUGPUGPU

Node

GPUGPUGPUGPU

Existing methods add maintenance and development costs

Page 11: GTC 2016 Europe: Breaking New Database Performance Records with GPUs

Bitfusion Boost: GPU Remote Virtualization

Hardware

VM Hypervisor

Drivers

Operating system

SDI

User Space

Hardware

VM Hypervisor

Drivers

Operating system

SDI

Hardware

VM Hypervisor

Drivers

Operating system

SDI

Open APIs

Custom APIs

Libraries

Application

Core Functions

Hardware

VM Hypervisor

Drivers

Operating system

SDI

• Binary-level API interception

• Distribute work across local and remote machines

application

remote servers

local server

System view

data and compute

pipelining

Advanced caching and data

directories

Auto service discovery, metering

Function redirection for advanced coprocessors

Supports the latest CUDA features including unified memory

Page 12: GTC 2016 Europe: Breaking New Database Performance Records with GPUs

Logi

cally

atta

ched

GPU

s

Virtually attached GPUs

CPU-only Node

48 Cores3 TB Memory

72 TB SSD Storage

BoostMassive Virtual NodeGPUGPUGPUGPU

GPUGPUGPUGPU

GPUGPUGPUGPU

GPUGPUGPUGPU

GPUGPUGPUGPU

GPUGPUGPUGPU

GPUGPUGPUGPU

GPUGPUGPUGPU

GPUGPUGPUGPU

GPUGPUGPUGPU

GPUGPUGPUGPU

GPUGPUGPUGPU

GPUGPUGPUGPU

GPUGPUGPUGPU

GPUGPUGPUGPU

GPUGPUGPUGPU

Racks with GPUs

GPU GPUGPU GPU

GPU GPUGPU GPU

GPU GPUGPU GPU

GPU GPUGPU GPU

GPU GPUGPU GPU

Creating the largest virtual GPU machines on demand

Page 13: GTC 2016 Europe: Breaking New Database Performance Records with GPUs

13

Unprecedented Speed at Scale

• 40 billions rows on 'select carrier_name, count(*) from flights2 group by carrier_name’ in 271ms

• 147 billion records scanned per second• 8X the number of records scanned previously

Combining: GPU-accelerated database + GPU Virtualization + Optimized CloudFor fastest database query times

Page 14: GTC 2016 Europe: Breaking New Database Performance Records with GPUs

14

App Specific Instance Configurations as Machine

Images

Resource Pooling:• Consolidate use of compute resources• Increase utilization• Lower capital costs

Resource Provisioning:• Enforce CPU, memory, utilization quotas• Effect QoS policy and guarantees• Maximize utilization and reduce costs

High availability:• Detect failures at app level• Rollback, failover, error detection• Events for higher level reporting

Heterogeneous Offload:• Leverage HPC hardware• Interpose vendor libraries• Retarget hot functions to efficient specialized devices

Scale-out:• Distribute and load balance load across systems• Scale performance on demand• Take advantage of runtime optimizations

Advanced Profiling:• Understand application

demands of the datacenter• Fine-grained data provides

unique insight• Precise recommendations for

capacity planning

Deep Learning Caffe Deep Learning Torch

Deep Learning TensorflowMedia Transcoding

Rendering Scientific Computing

Boost: Adding a broad set of GPU features to your application

Page 15: GTC 2016 Europe: Breaking New Database Performance Records with GPUs

15

In Summary

• Enable powerful GPU super nodes with Bitfusion Boost

• 60 days of collaboration with IBM and just a week to integrate

• Unprecedented database performance with MapD