SlideShare ist ein Scribd-Unternehmen logo
1 von 57
Downloaden Sie, um offline zu lesen
From 1 to1000 MIPS,[object Object],David J. DeWitt,[object Object],Microsoft Jim Gray Systems Lab,[object Object],Madison, Wisconsin,[object Object],dewitt@microsoft.com,[object Object],© 2009 Microsoft Corporation.  All rights reserved.  This presentation is for informational purposes only.  ,[object Object],Microsoft makes no warranties, express or implied in this presentation.,[object Object]
Wow.  They invited me back.  Thanks!!,[object Object],I guess some people did not fall asleep last year,[object Object],Still no new product announcements to make,[object Object],Still no motorcycle to ride across the stage,[object Object],No192-core servers to demo ,[object Object],But I did bring blue books for the quiz,[object Object],2,[object Object]
Who is this guy again?,[object Object],M,[object Object],Spent 32 years as a computer science professor at the University of Wisconsin,[object Object],Joined Microsoft in March 2008,[object Object],Run the Jim Gray Systems Lab in Madison, WI,[object Object],Lab is closely affiliated with the DB group at University of Wisconsin,[object Object],3  faculty and 8 graduate students working on projects,[object Object],Working on releases 1 and 2 of SQL Server Parallel Database Warehouse  ,[object Object],Tweet if you think SQL* would be a better name!,[object Object],3,[object Object]
If you skipped last year’s lecture …,[object Object],4,[object Object],Node K,[object Object],Node 2,[object Object],Node 1,[object Object],MEM,[object Object],MEM,[object Object],MEM,[object Object],CPU,[object Object],CPU,[object Object],CPU,[object Object],Interconnection Network,[object Object],Talked about parallel database technology and why products like SQL Server Parallel Data Warehouse employ a shared-nothing architectures to achieve scalability to 100s of nodes and petabytes of data,[object Object],…,[object Object]
Today …,[object Object],I want to dive in deep, really deep,[object Object],[object Object],Look at how trends in CPUs, memories, and disks  impact the designs of the database system running on each of those nodes ,[object Object],Database system specialization is inevitable over the next 10 years,[object Object],[object Object]
Specialized database products for transaction processing, data warehousing, main memory resident database, databases in the middle-tier, …
Evolution at work,[object Object]
  … to keep my boss happy:,[object Object],For the remainder of this talk I am switching to my “other” title:,[object Object],7,[object Object],David J. DeWittEmeritus ProfessorComputer Sciences DepartmentUniversity of Wisconsin,[object Object]
Talk Outline	,[object Object],Look at 30 years of technology trends in CPUs, memories, and disks,[object Object],Explain how these trends have impacted database system performance for OLTP and decision support workloads,[object Object],Why these trends are forcing DBMS to evolve ,[object Object],Some technical solutions,[object Object],Summary and conclusions,[object Object],8,[object Object]
9,[object Object],Query engine,[object Object],Buffer pool,[object Object],Time travel back to 1980,[object Object],Dominate hardware platform was the Digital VAX 11/780,[object Object],1 MIPS CPU w. 1KB of cache memory,[object Object],8 MB memory (maximum),[object Object],80 MB disk drives w. 1 MB/second transfer rate,[object Object],$250K purchase price!,[object Object],INGRES & Oracle were the dominant vendors,[object Object],Same basic DBMS architecture as is in use today,[object Object]
Since 1980                                     Today,[object Object],Basic RDMS design is essentially unchanged,[object Object],Except for scale-out using parallelism,[object Object],But the hardware landscape has changed dramatically:,[object Object],10,[object Object],Today,[object Object],1980,[object Object],Design Circa 1980,[object Object],RDBMS,[object Object],10,000X,[object Object],2,000X,[object Object],Disks,[object Object],Disks,[object Object],CPU,[object Object],CPU,[object Object],1,000X,[object Object],1,000X,[object Object],80 MB,[object Object],800 GB,[object Object],2 GIPS,[object Object],1 MIPS,[object Object],CPU ,[object Object],Caches,[object Object],Memory,[object Object],Memory,[object Object],CPU ,[object Object],Caches,[object Object],1 MB,[object Object],2 MB/CPU,[object Object],1 KB,[object Object],2 GB/CPU,[object Object]
A little closer look at 30 year disk trends,[object Object],Capacities:     80 MB  800 GB   -  10,000X,[object Object],Transfer rates: 1.2 MB/sec  80 MB/sec - 65X,[object Object],Avg. seek times:  30 ms  3 ms  - 10X,[object Object],(30 I/Os/sec   300 I/Os/sec)   ,[object Object],	The significant differences in these trends (10,000X vs. 65X vs. 10X) have had a huge impact on both OLTP and data warehouse workloads (as we will see),[object Object],11,[object Object]
Looking at OLTP,[object Object],1980,[object Object],1985,[object Object],1975,[object Object],[object Object]
Fastest system was IBM’s IMS Fastpath DBMS running on a top-of-the-line IBM 370 mainframe at 100 TPS with 4 disk I/Os per transaction:
100 TPS  400 disk I/Os/second
@ 30 I/Os/sec. per drive 14 drives
Fastest relational products could only do 10 TPS12,[object Object]
1990,[object Object],2000,[object Object],1980,[object Object],13,[object Object]
2020,[object Object],2030,[object Object],2009,[object Object],[object Object]
25,000 TPS  100,000 disk I/Os/second
@300 I/Os/sec per drive 330 drives!!!
Relative performance of CPUs and disks is totally out of whack14,[object Object]
OLTP Takeaway	,[object Object],The benefits from a 1,000x improvement in CPU performance and memory sizes are almost negated bythe 10X in disk accesses/second,[object Object],Forcing us to run our OLTP systems with 1000s of mostly empty disk drives,[object Object],No easy software fix, unfortunately,[object Object],SSDs provide the only real hope,[object Object],15,[object Object]
Turning to Data Warehousing,[object Object],Two key hardware trends have had a huge impact on the performance of single box relational DB systems:,[object Object],The imbalance between disk capacities and transfer rates,[object Object],The ever increasing gap between CPU performance and main memory bandwidth,[object Object],16,[object Object]
Looking at Disk Improvements,[object Object],Incredibly inexpensive drives (& processors) have made it possible to collect, store, and analyze huge quantities of data,[object Object],17,[object Object],Over the last 30 years,[object Object],Capacity:,[object Object],80MB  800GB,[object Object],10,000x,[object Object],Transfer Rates:,[object Object],1.2MB/sec  80MB/sec,[object Object],65x,[object Object],But, consider the metric  transfer bandwidth/byte,[object Object],1980:   1.2 MB/sec / 80 MB  =  0.015  ,[object Object],2009:    80 MB/sec / 800,000 MB =.0001,[object Object],When relative capacities are factored in, drives are 150X slower today!!! ,[object Object]
Another Viewpoint,[object Object],1980 ,[object Object],30 random I/Os/sec @ 8KB pages  240KB/sec,[object Object],Sequential transfers ran at 1.2 MB/sec,[object Object],Sequential/Random 5:1,[object Object],2009,[object Object],300 random I/Os/sec @ 8KB pages  2.4 MB/sec,[object Object],Sequential transfers run at 80 MB/sec,[object Object],Sequential/Random  33:1,[object Object],Takeaway:  DBMS must avoid doing random disk I/Os whenever possible,[object Object],18,[object Object]
Turning to CPU Trends,[object Object],Intel Core 2 Duo,[object Object],Vax 11/780 (1980),[object Object],19,[object Object],Key takeaway:  30 years ago the time required to access memory and execute an instruction were balanced.  ,[object Object],Today:,[object Object],Memory accesses are much slower,[object Object],Unit of transfer from memory to the L2 cache is only 64 bytes,[object Object],Together these have a large impact on DB performance ,[object Object],Die,[object Object],Cache line,[object Object],CPU,[object Object],CPU,[object Object],CPU,[object Object],L1 Cache,[object Object],L2 Cache,[object Object],L1 cache,[object Object],L1 cache,[object Object],Memory,[object Object],Memory,[object Object],64 bytes,[object Object],Memory page,[object Object],[object Object]
  2 - 8 MB shared L2 cache
  1 cycle/instruction
  2 cycles to access L1 cache
  20 cycles to access L2 cache
200 cycles to access memory
  8 KB L1 cache
 10 cycles/instruction
  6 cycles to access     memory,[object Object]
Intel Quad CPU PIII (4GB memory, 16KB L1D/I, 2MB Unified L2)
TPC-H queries on 10GB database w. 1GB buffer pool20,[object Object]
Breakdown of Memory Stalls,[object Object],21,[object Object]
Why So Many Stalls?,[object Object],L1 instruction cache stalls,[object Object],Combination of how a DBMS works and the sophistication of the compiler used to compile it,[object Object],Can be alleviated to some extent by applying code reorganization tools that rearrange the compiled code,[object Object],SQL Server does a much better job than DB2 at eliminating this class of stalls,[object Object],L2 data cache stalls,[object Object],Direct result of how rows of a table have been traditionally laid out on the DB pages,[object Object],Layout is technically termed a row-store,[object Object],22,[object Object]
23,[object Object],“Row-store” Layout,[object Object],As rows are loaded, they are grouped into pages and stored in a file ,[object Object],If average row length in customer table is 200 bytes, about 40 will fit on an 8K byte page,[object Object],Customers Table,[object Object],6   Dave      …         …      …      $9,000,[object Object],6   Dave      …         …      …      $9,000,[object Object],2   Sue         …         …     …         $500,[object Object],3   Ann         …         …     …      $1,700,[object Object],4   Jim          …         …     …     $1,500,[object Object],5   Liz          …         …      …            $0,[object Object],7   Sue        …         …      …      $1,010,[object Object],8   Bob        …         …      …           $50,[object Object],9   Jim         …         …      …      $1,300,[object Object],2   Sue         …         …     …         $500,[object Object],3   Ann         …         …     …      $1,700,[object Object],4   Jim          …         …     …     $1,500,[object Object],5   Liz          …         …      …            $0,[object Object],7   Sue        …         …      …      $1,010,[object Object],8   Bob        …         …      …           $50,[object Object],9   Jim         …         …      …      $1,300,[object Object],id  Name  Address  City  State  BalDue,[object Object],1   Bob         …         …     …      $3,000,[object Object],1   Bob         …         …     …      $3,000,[object Object],Page 1,[object Object],Nothing special here.  This is the standard way database systems have been laying out tables on disk since the mid 1970s.,[object Object],But technically it is called a “row store”,[object Object],Page 2,[object Object],Page 3,[object Object]
Why so many L2 cache misses?,[object Object],24,[object Object],(Again),[object Object],Select id, name, BalDue from Customers where BalDue > $500,[object Object],CPU,[object Object],Query summary:,[object Object],[object Object]
Up to 9 L1 and L2  cache misses  (one per tuple)L1 Cache,[object Object],..    $50 ,[object Object],.. $9000,[object Object],.. $1300,[object Object],.. $1500,[object Object],.. $3000,[object Object],.. $500,[object Object],.. $1700,[object Object],.. $1010,[object Object],..       $0,[object Object],64 bytes,[object Object],Page 1,[object Object],L2 Cache,[object Object],.. $1300,[object Object],.. $3000,[object Object],.. $500,[object Object],.. $1700,[object Object],.. $1500,[object Object],..       $0,[object Object],.. $1010,[object Object],..    $50 ,[object Object],.. $9000,[object Object],Page 2,[object Object],64 bytes,[object Object],Memory ,[object Object],(DBMS ,[object Object],Buffer Pool),[object Object],Don’t forget that:,[object Object],[object Object],Page 3,[object Object],8K bytes,[object Object],7  Sue   …    $1010,[object Object],8   Bob   …    $50,[object Object],9  Jim  …    $1,300,[object Object],4  Jim   …    $1,500,[object Object],5  Liz      …    $0,[object Object],6  Dave  …    $9,000,[object Object],1   Bob   …    $3000,[object Object],2   Sue   …    $500,[object Object],3  Ann   …    $1,700,[object Object],4 … $1500,[object Object],5 …     $0,[object Object],6 … $9000,[object Object],1 … $3000,[object Object],2 …  $500,[object Object],3 … $1700,[object Object],7 … $1010,[object Object],8 …    $50,[object Object],9 … $1300,[object Object]
Row Store Design Summary	,[object Object],25,[object Object],Can incur up to one L2 data cache miss per row processed if row size is greater than the size of the cache line,[object Object],DBMS transfers the entire row from disk to memory even though the query required just 3 attributes,[object Object],Design wastes precious disk bandwidth for read intensive workloads  ,[object Object],Don’t forget 10,000X  vs. 65X,[object Object],Is there an alternative physical organization?,[object Object],Yes, something called a column store,[object Object]
“Column Store” Table Layout,[object Object],id,[object Object],BalDue,[object Object],State,[object Object],City,[object Object],Address,[object Object],Name,[object Object],$3,000,[object Object],Bob,[object Object],Customers table – user’s view,[object Object],Customers table – one file/attribute,[object Object],$500,[object Object],Sue,[object Object],$1,700,[object Object],Anne,[object Object],$1,500,[object Object],Jim,[object Object],6   Dave      …         …      …      $9,000,[object Object],2   Sue         …         …     …         $500,[object Object],3   Ann         …         …     …      $1,700,[object Object],4   Jim          …         …     …     $1,500,[object Object],5   Liz          …         …      …            $0,[object Object],7   Sue        …         …      …      $1,010,[object Object],8   Bob        …         …      …           $50,[object Object],9   Jim         …         …      …      $1,300,[object Object],id  Name  Address  City  State  BalDue,[object Object],1   Bob         …         …     …      $3,000,[object Object],1,[object Object],2,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],3,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],4,[object Object],5,[object Object],$0,[object Object],Liz,[object Object],6,[object Object],$9,000,[object Object],Dave,[object Object],7,[object Object],$1,010,[object Object],Sue,[object Object],8,[object Object],$50,[object Object],…,[object Object],…,[object Object],…,[object Object],Bob,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],9,[object Object],$1,300,[object Object],Jim,[object Object],…,[object Object],…,[object Object],Tables are stored “column-wise” with all values from a single column stored in a single file,[object Object],26,[object Object]
Cache Misses With a Column Store,[object Object],27,[object Object],The Same ,[object Object],Example &,[object Object],Select id, name, BalDue from Customers where BalDue > $500,[object Object],CPU,[object Object],Takeaways:,[object Object],[object Object]
Processor stalls reduced by up to a factor of:	  8 (if BalDue values are 8 bytes)16 (if BalDue values are 4 bytes),[object Object],1300        ,[object Object],L1 Cache,[object Object],64 bytes,[object Object],L2 Cache,[object Object],1300        ,[object Object],64 bytes,[object Object],9000  1010  50   1300     ,[object Object],…       …      …         …     …..,[object Object],…       …      …         …     …..,[object Object],…       …      …         …     …..,[object Object],…       …      …         …     …..,[object Object],9000  1010  50   1300     ,[object Object],3000  500  1700,[object Object],3000  500  1700,[object Object],9000   1010  50,[object Object],3000   500   1700   1500   0   ,[object Object],3000   500   1700   1500   0   ,[object Object],9000   1010   50,[object Object],Memory,[object Object],8K bytes,[object Object],Caveats:,[object Object],[object Object]
Not showing disk I/Os required to read id and Name columns Id,[object Object],1500     0,[object Object],1500     0,[object Object],Bob   Sue   Ann   Jim    Liz,[object Object],Name,[object Object],Dave  Sue   Bob   Jim  ,[object Object],BalDue,[object Object],1   2   3   4   5   6   7   8   9,[object Object],Street,[object Object]
A Concrete Example,[object Object],Assume: ,[object Object],   Customer table has 10M rows, 200 bytes/row (2GB total size),[object Object],   Id and BalDue values are each 4 bytes long, Name is 20 bytes,[object Object],Query:,[object Object],   Select id, Name, BalDue from Customer where BalDue > $1000,[object Object],Row store execution,[object Object],Scan 10M rows (2GB) @ 80MB/sec = 25 sec.,[object Object],Column store execution,[object Object],     Scan 3 columns,  each with 10M entries 280MB@80MB/sec = 3.5 sec. ,[object Object],		(id 40MB, Name 200MB, BalDue 40MB),[object Object],About a 7X performance improvement for this query!! ,[object Object],	But we can do even better using compression,[object Object],28,[object Object]
Summarizing:,[object Object],Storing tables as a set of columns:,[object Object],Significantly reduces the amount of disk I/O required to execute a query,[object Object],“Select * from Customer where …” will neverbe faster,[object Object],Improves CPU performance by reducing memory stalls caused by L2 data cache misses,[object Object],Facilitates the application of VERY aggressive compression techniques, reducing disk I/Os and L2 cache misses even further,[object Object],29,[object Object]
Column Store Implementation Issues,[object Object],30,[object Object]
Physical Representation Alternatives,[object Object],Three main alternatives:,[object Object],DSM (1985 – Copeland & Koshafian),[object Object],Modified B-tree (2005 – DeWitt & Ramamurthy),[object Object],“Positional” representation (Sybase IQ and C-Store/Vertica),[object Object],31,[object Object],Sales (Quarter, ProdID, Price) order by Quarter, ProdID,[object Object],1,[object Object],Q1,[object Object],5,[object Object],ProdID,[object Object],Quarter,[object Object],Price,[object Object],1,[object Object],Q1,[object Object],7,[object Object],1,[object Object],Q1,[object Object],2,[object Object],1,[object Object],Q1,[object Object],9,[object Object],1,[object Object],Q1,[object Object],6,[object Object],2,[object Object],Q1,[object Object],8,[object Object],2,[object Object],Q1,[object Object],5,[object Object],…,[object Object],…,[object Object],…,[object Object],1,[object Object],Q2,[object Object],3,[object Object],1,[object Object],Q2,[object Object],8,[object Object],1,[object Object],Q2,[object Object],1,[object Object],2,[object Object],Q2,[object Object],4,[object Object],…,[object Object],…,[object Object],…,[object Object]
DSM Model (1985),[object Object],32,[object Object],Sales (Quarter, ProdID, Price) order by Quarter, ProdID,[object Object],For each column, store an ID and the value of the column,[object Object],Quarter,[object Object],RowID,[object Object],Price,[object Object],RowID,[object Object],ProdID,[object Object],1,[object Object],RowID,[object Object],1,[object Object],Q1,[object Object],5,[object Object],Q1,[object Object],1,[object Object],5,[object Object],1,[object Object],1,[object Object],ProdID,[object Object],Quarter,[object Object],Price,[object Object],1,[object Object],Q1,[object Object],7,[object Object],Q1,[object Object],2,[object Object],7,[object Object],2,[object Object],1,[object Object],2,[object Object],[object Object]
Design can waste significant space storing all the RowIDs
Difficult to compress
Implementation typically uses a B-tree1,[object Object],Q1,[object Object],2,[object Object],Q1,[object Object],3,[object Object],2,[object Object],3,[object Object],1,[object Object],3,[object Object],1,[object Object],Q1,[object Object],9,[object Object],Q1,[object Object],4,[object Object],9,[object Object],4,[object Object],1,[object Object],4,[object Object],1,[object Object],Q1,[object Object],6,[object Object],Q1,[object Object],5,[object Object],6,[object Object],5,[object Object],1,[object Object],5,[object Object],2,[object Object],Q1,[object Object],8,[object Object],Q1,[object Object],6,[object Object],8,[object Object],6,[object Object],2,[object Object],6,[object Object],2,[object Object],Q1,[object Object],5,[object Object],Q1,[object Object],7,[object Object],5,[object Object],7,[object Object],2,[object Object],7,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],1,[object Object],Q2,[object Object],3,[object Object],Q2,[object Object],301,[object Object],3,[object Object],301,[object Object],1,[object Object],301,[object Object],1,[object Object],Q2,[object Object],8,[object Object],Q2,[object Object],302,[object Object],8,[object Object],302,[object Object],1,[object Object],302,[object Object],1,[object Object],Q2,[object Object],1,[object Object],Q2,[object Object],303,[object Object],1,[object Object],303,[object Object],1,[object Object],303,[object Object],2,[object Object],Q2,[object Object],4,[object Object],Q2,[object Object],304,[object Object],4,[object Object],304,[object Object],2,[object Object],304,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object]
Alternative B-Tree representations,[object Object],33,[object Object],Dense B-tree on RowID  – one entry for each value in column,[object Object],Quarter,[object Object],RowID,[object Object],Q1,[object Object],1,[object Object],…                …,[object Object],Q1,[object Object],2,[object Object],Q1,[object Object],3,[object Object],Q1,[object Object],4,[object Object],Q1,[object Object],5,[object Object],301,[object Object],Q2,[object Object],302,[object Object],Q2,[object Object],302,[object Object],Q2,[object Object],302,[object Object],Q2,[object Object],1,[object Object],Q1,[object Object],2,[object Object],Q1,[object Object],3,[object Object],Q1,[object Object],4,[object Object],Q1,[object Object],…,[object Object],…,[object Object],1,[object Object],Q1,[object Object],301,[object Object],Q2,[object Object],956,[object Object],Q3,[object Object],1501,[object Object],Q4,[object Object],…,[object Object],…,[object Object],Q1,[object Object],6,[object Object],Sparse B-tree on RowID  – one entry for each group of identical column values,[object Object],Q1,[object Object],7,[object Object],…,[object Object],…,[object Object],Q2,[object Object],301,[object Object],300,[object Object],…                …,[object Object],Q2,[object Object],302,[object Object],1500,[object Object],Q2,[object Object],303,[object Object],Q2,[object Object],304,[object Object],…,[object Object],…,[object Object]
Positional Representation,[object Object],Each column stored as a separate file with values stored one after another,[object Object],No typical “slotted page” indirection or record headers ,[object Object],Store only column values, no RowIDs,[object Object],Associated RowIDs computed during query processing,[object Object],Aggressively compress,[object Object],34,[object Object],ProdID,[object Object],Quarter,[object Object],Price,[object Object],1,[object Object],Q1,[object Object],5,[object Object],1,[object Object],Q1,[object Object],5,[object Object],ProdID,[object Object],Quarter,[object Object],Price,[object Object],1,[object Object],Q1,[object Object],7,[object Object],1,[object Object],Q1,[object Object],7,[object Object],1,[object Object],Q1,[object Object],2,[object Object],1,[object Object],Q1,[object Object],2,[object Object],1,[object Object],Q1,[object Object],9,[object Object],1,[object Object],Q1,[object Object],9,[object Object],1,[object Object],Q1,[object Object],6,[object Object],1,[object Object],Q1,[object Object],6,[object Object],2,[object Object],Q1,[object Object],8,[object Object],2,[object Object],Q1,[object Object],8,[object Object],2,[object Object],Q1,[object Object],5,[object Object],2,[object Object],Q1,[object Object],5,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],1,[object Object],Q2,[object Object],3,[object Object],1,[object Object],Q2,[object Object],3,[object Object],1,[object Object],Q2,[object Object],8,[object Object],1,[object Object],Q2,[object Object],8,[object Object],1,[object Object],Q2,[object Object],1,[object Object],1,[object Object],Q2,[object Object],1,[object Object],2,[object Object],Q2,[object Object],4,[object Object],2,[object Object],Q2,[object Object],4,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object],…,[object Object]

Weitere ähnliche Inhalte

Ähnlich wie PASS Summit 2009 Keynote Dave DeWitt

Designs, Lessons and Advice from Building Large Distributed Systems
Designs, Lessons and Advice from Building Large Distributed SystemsDesigns, Lessons and Advice from Building Large Distributed Systems
Designs, Lessons and Advice from Building Large Distributed SystemsDaehyeok Kim
 
Data storage systems
Data storage systemsData storage systems
Data storage systemsdelimitry
 
All About Storeconfigs
All About StoreconfigsAll About Storeconfigs
All About StoreconfigsBrice Figureau
 
Data oriented design and c++
Data oriented design and c++Data oriented design and c++
Data oriented design and c++Mike Acton
 
What makes a LDAP server running fast ? An bit of insight about the various b...
What makes a LDAP server running fast ? An bit of insight about the various b...What makes a LDAP server running fast ? An bit of insight about the various b...
What makes a LDAP server running fast ? An bit of insight about the various b...LDAPCon
 
Future of computing is boring (and that is exciting!)
Future of computing is boring (and that is exciting!) Future of computing is boring (and that is exciting!)
Future of computing is boring (and that is exciting!) alekn
 
Linux and H/W optimizations for MySQL
Linux and H/W optimizations for MySQLLinux and H/W optimizations for MySQL
Linux and H/W optimizations for MySQLYoshinori Matsunobu
 
Storage: Alternate Futures
Storage: Alternate FuturesStorage: Alternate Futures
Storage: Alternate Futures小新 制造
 
Exchange 2010 storage improvements
Exchange 2010 storage improvementsExchange 2010 storage improvements
Exchange 2010 storage improvementsNathan Winters
 
14 scaleabilty wics
14 scaleabilty wics14 scaleabilty wics
14 scaleabilty wicsashish61_scs
 
Tips & Tricks On Architecting Windows Azure For Costs
Tips & Tricks On Architecting Windows Azure For CostsTips & Tricks On Architecting Windows Azure For Costs
Tips & Tricks On Architecting Windows Azure For CostsNuno Godinho
 
How Shit Works: Storage
How Shit Works: StorageHow Shit Works: Storage
How Shit Works: StorageTomer Gabel
 
Performance Tipping Points - Hitting Hardware Bottlenecks
Performance Tipping Points - Hitting Hardware BottlenecksPerformance Tipping Points - Hitting Hardware Bottlenecks
Performance Tipping Points - Hitting Hardware BottlenecksMongoDB
 
E Science As A Lens On The World Lazowska
E Science As A Lens On The World   LazowskaE Science As A Lens On The World   Lazowska
E Science As A Lens On The World Lazowskaguest43b4df3
 
E Science As A Lens On The World Lazowska
E Science As A Lens On The World   LazowskaE Science As A Lens On The World   Lazowska
E Science As A Lens On The World LazowskaWCET
 
The InnoDB Storage Engine for MySQL
The InnoDB Storage Engine for MySQLThe InnoDB Storage Engine for MySQL
The InnoDB Storage Engine for MySQLMorgan Tocker
 

Ähnlich wie PASS Summit 2009 Keynote Dave DeWitt (20)

Designs, Lessons and Advice from Building Large Distributed Systems
Designs, Lessons and Advice from Building Large Distributed SystemsDesigns, Lessons and Advice from Building Large Distributed Systems
Designs, Lessons and Advice from Building Large Distributed Systems
 
Data storage systems
Data storage systemsData storage systems
Data storage systems
 
All About Storeconfigs
All About StoreconfigsAll About Storeconfigs
All About Storeconfigs
 
Data oriented design and c++
Data oriented design and c++Data oriented design and c++
Data oriented design and c++
 
What makes a LDAP server running fast ? An bit of insight about the various b...
What makes a LDAP server running fast ? An bit of insight about the various b...What makes a LDAP server running fast ? An bit of insight about the various b...
What makes a LDAP server running fast ? An bit of insight about the various b...
 
The Smug Mug Tale
The Smug Mug TaleThe Smug Mug Tale
The Smug Mug Tale
 
IO Dubi Lebel
IO Dubi LebelIO Dubi Lebel
IO Dubi Lebel
 
Future of computing is boring (and that is exciting!)
Future of computing is boring (and that is exciting!) Future of computing is boring (and that is exciting!)
Future of computing is boring (and that is exciting!)
 
Linux and H/W optimizations for MySQL
Linux and H/W optimizations for MySQLLinux and H/W optimizations for MySQL
Linux and H/W optimizations for MySQL
 
C 4
C 4C 4
C 4
 
Media storage
Media storageMedia storage
Media storage
 
Storage: Alternate Futures
Storage: Alternate FuturesStorage: Alternate Futures
Storage: Alternate Futures
 
Exchange 2010 storage improvements
Exchange 2010 storage improvementsExchange 2010 storage improvements
Exchange 2010 storage improvements
 
14 scaleabilty wics
14 scaleabilty wics14 scaleabilty wics
14 scaleabilty wics
 
Tips & Tricks On Architecting Windows Azure For Costs
Tips & Tricks On Architecting Windows Azure For CostsTips & Tricks On Architecting Windows Azure For Costs
Tips & Tricks On Architecting Windows Azure For Costs
 
How Shit Works: Storage
How Shit Works: StorageHow Shit Works: Storage
How Shit Works: Storage
 
Performance Tipping Points - Hitting Hardware Bottlenecks
Performance Tipping Points - Hitting Hardware BottlenecksPerformance Tipping Points - Hitting Hardware Bottlenecks
Performance Tipping Points - Hitting Hardware Bottlenecks
 
E Science As A Lens On The World Lazowska
E Science As A Lens On The World   LazowskaE Science As A Lens On The World   Lazowska
E Science As A Lens On The World Lazowska
 
E Science As A Lens On The World Lazowska
E Science As A Lens On The World   LazowskaE Science As A Lens On The World   Lazowska
E Science As A Lens On The World Lazowska
 
The InnoDB Storage Engine for MySQL
The InnoDB Storage Engine for MySQLThe InnoDB Storage Engine for MySQL
The InnoDB Storage Engine for MySQL
 

Mehr von Mark Ginnebaugh

Automating Microsoft Power BI Creations 2015
Automating Microsoft Power BI Creations 2015Automating Microsoft Power BI Creations 2015
Automating Microsoft Power BI Creations 2015Mark Ginnebaugh
 
Microsoft SQL Server Analysis Services (SSAS) - A Practical Introduction
Microsoft SQL Server Analysis Services (SSAS) - A Practical Introduction Microsoft SQL Server Analysis Services (SSAS) - A Practical Introduction
Microsoft SQL Server Analysis Services (SSAS) - A Practical Introduction Mark Ginnebaugh
 
Platfora - An Analytics Sandbox In A World Of Big Data
Platfora - An Analytics Sandbox In A World Of Big DataPlatfora - An Analytics Sandbox In A World Of Big Data
Platfora - An Analytics Sandbox In A World Of Big DataMark Ginnebaugh
 
Microsoft SQL Server Relational Databases and Primary Keys
Microsoft SQL Server Relational Databases and Primary KeysMicrosoft SQL Server Relational Databases and Primary Keys
Microsoft SQL Server Relational Databases and Primary KeysMark Ginnebaugh
 
DesignMind Microsoft Business Intelligence SQL Server
DesignMind Microsoft Business Intelligence SQL ServerDesignMind Microsoft Business Intelligence SQL Server
DesignMind Microsoft Business Intelligence SQL ServerMark Ginnebaugh
 
San Francisco Bay Area SQL Server July 2013 meetings
San Francisco Bay Area SQL Server July 2013 meetingsSan Francisco Bay Area SQL Server July 2013 meetings
San Francisco Bay Area SQL Server July 2013 meetingsMark Ginnebaugh
 
Silicon Valley SQL Server User Group June 2013
Silicon Valley SQL Server User Group June 2013Silicon Valley SQL Server User Group June 2013
Silicon Valley SQL Server User Group June 2013Mark Ginnebaugh
 
Microsoft SQL Server Continuous Integration
Microsoft SQL Server Continuous IntegrationMicrosoft SQL Server Continuous Integration
Microsoft SQL Server Continuous IntegrationMark Ginnebaugh
 
Hortonworks Big Data & Hadoop
Hortonworks Big Data & HadoopHortonworks Big Data & Hadoop
Hortonworks Big Data & HadoopMark Ginnebaugh
 
Microsoft SQL Server Physical Join Operators
Microsoft SQL Server Physical Join OperatorsMicrosoft SQL Server Physical Join Operators
Microsoft SQL Server Physical Join OperatorsMark Ginnebaugh
 
Microsoft PowerPivot & Power View in Excel 2013
Microsoft PowerPivot & Power View in Excel 2013Microsoft PowerPivot & Power View in Excel 2013
Microsoft PowerPivot & Power View in Excel 2013Mark Ginnebaugh
 
Microsoft Data Warehouse Business Intelligence Lifecycle - The Kimball Approach
Microsoft Data Warehouse Business Intelligence Lifecycle - The Kimball ApproachMicrosoft Data Warehouse Business Intelligence Lifecycle - The Kimball Approach
Microsoft Data Warehouse Business Intelligence Lifecycle - The Kimball ApproachMark Ginnebaugh
 
Fusion-io Memory Flash for Microsoft SQL Server 2012
Fusion-io Memory Flash for Microsoft SQL Server 2012Fusion-io Memory Flash for Microsoft SQL Server 2012
Fusion-io Memory Flash for Microsoft SQL Server 2012Mark Ginnebaugh
 
Microsoft Data Mining 2012
Microsoft Data Mining 2012Microsoft Data Mining 2012
Microsoft Data Mining 2012Mark Ginnebaugh
 
Microsoft SQL Server PASS News August 2012
Microsoft SQL Server PASS News August 2012Microsoft SQL Server PASS News August 2012
Microsoft SQL Server PASS News August 2012Mark Ginnebaugh
 
Business Intelligence Dashboard Design Best Practices
Business Intelligence Dashboard Design Best PracticesBusiness Intelligence Dashboard Design Best Practices
Business Intelligence Dashboard Design Best PracticesMark Ginnebaugh
 
Microsoft Mobile Business Intelligence
Microsoft Mobile Business Intelligence Microsoft Mobile Business Intelligence
Microsoft Mobile Business Intelligence Mark Ginnebaugh
 
Microsoft SQL Server 2012 Cloud Ready
Microsoft SQL Server 2012 Cloud ReadyMicrosoft SQL Server 2012 Cloud Ready
Microsoft SQL Server 2012 Cloud ReadyMark Ginnebaugh
 
Microsoft SQL Server 2012 Master Data Services
Microsoft SQL Server 2012 Master Data ServicesMicrosoft SQL Server 2012 Master Data Services
Microsoft SQL Server 2012 Master Data ServicesMark Ginnebaugh
 
Microsoft SQL Server PowerPivot
Microsoft SQL Server PowerPivotMicrosoft SQL Server PowerPivot
Microsoft SQL Server PowerPivotMark Ginnebaugh
 

Mehr von Mark Ginnebaugh (20)

Automating Microsoft Power BI Creations 2015
Automating Microsoft Power BI Creations 2015Automating Microsoft Power BI Creations 2015
Automating Microsoft Power BI Creations 2015
 
Microsoft SQL Server Analysis Services (SSAS) - A Practical Introduction
Microsoft SQL Server Analysis Services (SSAS) - A Practical Introduction Microsoft SQL Server Analysis Services (SSAS) - A Practical Introduction
Microsoft SQL Server Analysis Services (SSAS) - A Practical Introduction
 
Platfora - An Analytics Sandbox In A World Of Big Data
Platfora - An Analytics Sandbox In A World Of Big DataPlatfora - An Analytics Sandbox In A World Of Big Data
Platfora - An Analytics Sandbox In A World Of Big Data
 
Microsoft SQL Server Relational Databases and Primary Keys
Microsoft SQL Server Relational Databases and Primary KeysMicrosoft SQL Server Relational Databases and Primary Keys
Microsoft SQL Server Relational Databases and Primary Keys
 
DesignMind Microsoft Business Intelligence SQL Server
DesignMind Microsoft Business Intelligence SQL ServerDesignMind Microsoft Business Intelligence SQL Server
DesignMind Microsoft Business Intelligence SQL Server
 
San Francisco Bay Area SQL Server July 2013 meetings
San Francisco Bay Area SQL Server July 2013 meetingsSan Francisco Bay Area SQL Server July 2013 meetings
San Francisco Bay Area SQL Server July 2013 meetings
 
Silicon Valley SQL Server User Group June 2013
Silicon Valley SQL Server User Group June 2013Silicon Valley SQL Server User Group June 2013
Silicon Valley SQL Server User Group June 2013
 
Microsoft SQL Server Continuous Integration
Microsoft SQL Server Continuous IntegrationMicrosoft SQL Server Continuous Integration
Microsoft SQL Server Continuous Integration
 
Hortonworks Big Data & Hadoop
Hortonworks Big Data & HadoopHortonworks Big Data & Hadoop
Hortonworks Big Data & Hadoop
 
Microsoft SQL Server Physical Join Operators
Microsoft SQL Server Physical Join OperatorsMicrosoft SQL Server Physical Join Operators
Microsoft SQL Server Physical Join Operators
 
Microsoft PowerPivot & Power View in Excel 2013
Microsoft PowerPivot & Power View in Excel 2013Microsoft PowerPivot & Power View in Excel 2013
Microsoft PowerPivot & Power View in Excel 2013
 
Microsoft Data Warehouse Business Intelligence Lifecycle - The Kimball Approach
Microsoft Data Warehouse Business Intelligence Lifecycle - The Kimball ApproachMicrosoft Data Warehouse Business Intelligence Lifecycle - The Kimball Approach
Microsoft Data Warehouse Business Intelligence Lifecycle - The Kimball Approach
 
Fusion-io Memory Flash for Microsoft SQL Server 2012
Fusion-io Memory Flash for Microsoft SQL Server 2012Fusion-io Memory Flash for Microsoft SQL Server 2012
Fusion-io Memory Flash for Microsoft SQL Server 2012
 
Microsoft Data Mining 2012
Microsoft Data Mining 2012Microsoft Data Mining 2012
Microsoft Data Mining 2012
 
Microsoft SQL Server PASS News August 2012
Microsoft SQL Server PASS News August 2012Microsoft SQL Server PASS News August 2012
Microsoft SQL Server PASS News August 2012
 
Business Intelligence Dashboard Design Best Practices
Business Intelligence Dashboard Design Best PracticesBusiness Intelligence Dashboard Design Best Practices
Business Intelligence Dashboard Design Best Practices
 
Microsoft Mobile Business Intelligence
Microsoft Mobile Business Intelligence Microsoft Mobile Business Intelligence
Microsoft Mobile Business Intelligence
 
Microsoft SQL Server 2012 Cloud Ready
Microsoft SQL Server 2012 Cloud ReadyMicrosoft SQL Server 2012 Cloud Ready
Microsoft SQL Server 2012 Cloud Ready
 
Microsoft SQL Server 2012 Master Data Services
Microsoft SQL Server 2012 Master Data ServicesMicrosoft SQL Server 2012 Master Data Services
Microsoft SQL Server 2012 Master Data Services
 
Microsoft SQL Server PowerPivot
Microsoft SQL Server PowerPivotMicrosoft SQL Server PowerPivot
Microsoft SQL Server PowerPivot
 

Kürzlich hochgeladen

UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8DianaGray10
 
Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.YounusS2
 
Introduction to Matsuo Laboratory (ENG).pptx
Introduction to Matsuo Laboratory (ENG).pptxIntroduction to Matsuo Laboratory (ENG).pptx
Introduction to Matsuo Laboratory (ENG).pptxMatsuo Lab
 
AI Fame Rush Review – Virtual Influencer Creation In Just Minutes
AI Fame Rush Review – Virtual Influencer Creation In Just MinutesAI Fame Rush Review – Virtual Influencer Creation In Just Minutes
AI Fame Rush Review – Virtual Influencer Creation In Just MinutesMd Hossain Ali
 
Spring24-Release Overview - Wellingtion User Group-1.pdf
Spring24-Release Overview - Wellingtion User Group-1.pdfSpring24-Release Overview - Wellingtion User Group-1.pdf
Spring24-Release Overview - Wellingtion User Group-1.pdfAnna Loughnan Colquhoun
 
Cloud Revolution: Exploring the New Wave of Serverless Spatial Data
Cloud Revolution: Exploring the New Wave of Serverless Spatial DataCloud Revolution: Exploring the New Wave of Serverless Spatial Data
Cloud Revolution: Exploring the New Wave of Serverless Spatial DataSafe Software
 
Do we need a new standard for visualizing the invisible?
Do we need a new standard for visualizing the invisible?Do we need a new standard for visualizing the invisible?
Do we need a new standard for visualizing the invisible?SANGHEE SHIN
 
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPA
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPAAnypoint Code Builder , Google Pub sub connector and MuleSoft RPA
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPAshyamraj55
 
UiPath Studio Web workshop series - Day 7
UiPath Studio Web workshop series - Day 7UiPath Studio Web workshop series - Day 7
UiPath Studio Web workshop series - Day 7DianaGray10
 
Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Commit University
 
PicPay - GenAI Finance Assistant - ChatGPT for Customer Service
PicPay - GenAI Finance Assistant - ChatGPT for Customer ServicePicPay - GenAI Finance Assistant - ChatGPT for Customer Service
PicPay - GenAI Finance Assistant - ChatGPT for Customer ServiceRenan Moreira de Oliveira
 
Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1DianaGray10
 
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...Aggregage
 
Things you didn't know you can use in your Salesforce
Things you didn't know you can use in your SalesforceThings you didn't know you can use in your Salesforce
Things you didn't know you can use in your SalesforceMartin Humpolec
 
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019IES VE
 
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesHow to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesThousandEyes
 
NIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 WorkshopNIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 WorkshopBachir Benyammi
 
Bird eye's view on Camunda open source ecosystem
Bird eye's view on Camunda open source ecosystemBird eye's view on Camunda open source ecosystem
Bird eye's view on Camunda open source ecosystemAsko Soukka
 
Empowering Africa's Next Generation: The AI Leadership Blueprint
Empowering Africa's Next Generation: The AI Leadership BlueprintEmpowering Africa's Next Generation: The AI Leadership Blueprint
Empowering Africa's Next Generation: The AI Leadership BlueprintMahmoud Rabie
 
UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1DianaGray10
 

Kürzlich hochgeladen (20)

UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8
 
Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.
 
Introduction to Matsuo Laboratory (ENG).pptx
Introduction to Matsuo Laboratory (ENG).pptxIntroduction to Matsuo Laboratory (ENG).pptx
Introduction to Matsuo Laboratory (ENG).pptx
 
AI Fame Rush Review – Virtual Influencer Creation In Just Minutes
AI Fame Rush Review – Virtual Influencer Creation In Just MinutesAI Fame Rush Review – Virtual Influencer Creation In Just Minutes
AI Fame Rush Review – Virtual Influencer Creation In Just Minutes
 
Spring24-Release Overview - Wellingtion User Group-1.pdf
Spring24-Release Overview - Wellingtion User Group-1.pdfSpring24-Release Overview - Wellingtion User Group-1.pdf
Spring24-Release Overview - Wellingtion User Group-1.pdf
 
Cloud Revolution: Exploring the New Wave of Serverless Spatial Data
Cloud Revolution: Exploring the New Wave of Serverless Spatial DataCloud Revolution: Exploring the New Wave of Serverless Spatial Data
Cloud Revolution: Exploring the New Wave of Serverless Spatial Data
 
Do we need a new standard for visualizing the invisible?
Do we need a new standard for visualizing the invisible?Do we need a new standard for visualizing the invisible?
Do we need a new standard for visualizing the invisible?
 
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPA
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPAAnypoint Code Builder , Google Pub sub connector and MuleSoft RPA
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPA
 
UiPath Studio Web workshop series - Day 7
UiPath Studio Web workshop series - Day 7UiPath Studio Web workshop series - Day 7
UiPath Studio Web workshop series - Day 7
 
Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)
 
PicPay - GenAI Finance Assistant - ChatGPT for Customer Service
PicPay - GenAI Finance Assistant - ChatGPT for Customer ServicePicPay - GenAI Finance Assistant - ChatGPT for Customer Service
PicPay - GenAI Finance Assistant - ChatGPT for Customer Service
 
Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1
 
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...
 
Things you didn't know you can use in your Salesforce
Things you didn't know you can use in your SalesforceThings you didn't know you can use in your Salesforce
Things you didn't know you can use in your Salesforce
 
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019
 
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesHow to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
 
NIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 WorkshopNIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 Workshop
 
Bird eye's view on Camunda open source ecosystem
Bird eye's view on Camunda open source ecosystemBird eye's view on Camunda open source ecosystem
Bird eye's view on Camunda open source ecosystem
 
Empowering Africa's Next Generation: The AI Leadership Blueprint
Empowering Africa's Next Generation: The AI Leadership BlueprintEmpowering Africa's Next Generation: The AI Leadership Blueprint
Empowering Africa's Next Generation: The AI Leadership Blueprint
 
UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1
 

PASS Summit 2009 Keynote Dave DeWitt

Hinweis der Redaktion

  1. The “evolution” comment is not clear…
  2. CPUs: 1 MIPS  2 GIPS  2,000XCPU Caches: 1K  1MB  1,000XMemory: 2MB/CPU  2GB/CPU  1,000XDisks: 80 MB  800 GB  10,000X
  3. Why are dates so important here?