Apenas para uma revisão de 2020 das previsões para 2025:
Nos últimos 44 anos da tecnologia de circuitos integrados, os processadores clássicos (não quânticos) evoluíram literal e fisicamente "Per Aspera ad Astra" . A última década evidenciou que o processo clássico chegou perto de alguns obstáculos, que não têm um caminho físico viável à frente.
Number of logical corespode e pode crescer, mas não mais do que dificilmente, se não impossível, contornar o teto baseado na física já atingido pode e pode crescer, ainda menos do que (potência, ruído, "relógio") pode crescer, ainda que problemas com a distribuição de energia e a dissipação de calor o aumento pode crescer, tendo benefícios diretos com grandes pegadas de cache e benefícios de E / S de memória mais rápidos e amplos e benefícios indiretos da troca de contexto forçada pelo sistema com menos frequência, pois podemos ter mais núcleos para dividir outros threads / processos entreO(n^2~3)
Frequency [MHz]
Transistor CountO(n^2~3)
Power [W]
Single Thread Perf
(Os créditos vão para Leonardo Suriano e Karl Rupp)
2020: Still some improvements, prediction for 2025
-------------------------------------------------------------------------
0.1 ns - NOP
0.3 ns - XOR, ADD, SUB
0.5 ns - CPU L1 dCACHE reference (1st introduced in late 80-ies )
0.9 ns - JMP SHORT
1 ns - speed-of-light (a photon) travel a 1 ft (30.5cm) distance -- will stay, throughout any foreseeable future :o)
?~~~~~~~~~~~ 1 ns - MUL ( i**2 = MUL i, i )~~~~~~~~~ doing this 1,000 x is 1 [us]; 1,000,000 x is 1 [ms]; 1,000,000,000 x is 1 [s] ~~~~~~~~~~~~~~~~~~~~~~~~~
3~4 ns - CPU L2 CACHE reference (2020/Q1)
5 ns - CPU L1 iCACHE Branch mispredict
7 ns - CPU L2 CACHE reference
10 ns - DIV
19 ns - CPU L3 CACHE reference (2020/Q1 considered slow on 28c Skylake)
71 ns - CPU cross-QPI/NUMA best case on XEON E5-46*
100 ns - MUTEX lock/unlock
100 ns - own DDR MEMORY reference
135 ns - CPU cross-QPI/NUMA best case on XEON E7-*
202 ns - CPU cross-QPI/NUMA worst case on XEON E7-*
325 ns - CPU cross-QPI/NUMA worst case on XEON E5-46*
|Q>~~~~~ 5,000 ns - QPU on-chip QUBO ( quantum annealer minimiser 1 Qop )
10,000 ns - Compress 1K bytes with a Zippy PROCESS
20,000 ns - Send 2K bytes over 1 Gbps NETWORK
250,000 ns - Read 1 MB sequentially from MEMORY
500,000 ns - Round trip within a same DataCenter
?~~~ 2,500,000 ns - Read 10 MB sequentially from MEMORY~~(about an empty python process to copy on spawn)~~~~ x ( 1 + nProcesses ) on spawned process instantiation(s), yet an empty python interpreter is indeed not a real-world, production-grade use-case, is it?
10,000,000 ns - DISK seek
10,000,000 ns - Read 1 MB sequentially from NETWORK
?~~ 25,000,000 ns - Read 100 MB sequentially from MEMORY~~(somewhat light python process to copy on spawn)~~~~ x ( 1 + nProcesses ) on spawned process instantiation(s)
30,000,000 ns - Read 1 MB sequentially from a DISK
?~~ 36,000,000 ns - Pickle.dump() SER a 10 MB object for IPC-transfer and remote DES in spawned process~~~~~~~~ x ( 2 ) for a single 10MB parameter-payload SER/DES + add an IPC-transport costs thereof or NETWORK-grade transport costs, if going into [distributed-computing] model Cluster ecosystem
150,000,000 ns - Send a NETWORK packet CA -> Netherlands
| | | |
| | | ns|
| | us|
| ms|
Apenas para uma revisão de 2015 das previsões para 2020:
Still some improvements, prediction for 2020 (Ref. olibre's answer below)
-------------------------------------------------------------------------
16 000 ns ( 16 µs) SSD random read (olibre's note: should be less)
500 000 ns ( ½ ms) Round trip in datacenter
2 000 000 ns ( 2 ms) HDD random read (seek)
In 2015 there are currently available:
========================================================================
820 ns ( 0.8µs) random read from a SSD-DataPlane
1 200 ns ( 1.2µs) Round trip in datacenter
1 200 ns ( 1.2µs) random read from a HDD-DataPlane
Apenas para comparar o cenário de latência de CPU e GPU:
Não é uma tarefa fácil comparar até mesmo as mais simples linhas de CPU / cache / DRAM (mesmo em um modelo uniforme de acesso à memória), em que a velocidade da DRAM é um fator na determinação da latência e da latência carregada (sistema saturado), onde o último governa e é algo que os aplicativos corporativos experimentarão mais do que um sistema ocioso e totalmente descarregado.
+----------------------------------- 5,6,7,8,9,..12,15,16
| +--- 1066,1333,..2800..3300
v v
First word = ( ( CAS latency * 2 ) + ( 1 - 1 ) ) / Data Rate
Fourth word = ( ( CAS latency * 2 ) + ( 4 - 1 ) ) / Data Rate
Eighth word = ( ( CAS latency * 2 ) + ( 8 - 1 ) ) / Data Rate
^----------------------- 7x .. difference
********************************
So:
===
resulting DDR3-side latencies are between _____________
3.03 ns ^
|
36.58 ns ___v_ based on DDR3 HW facts
Os mecanismos de GPU receberam muito marketing técnico, enquanto profundas dependências internas são fundamentais para entender os pontos fortes reais e também os pontos fracos reais que essas arquiteturas experimentam na prática (geralmente muito diferentes das expectativas assobiadas pelo marketing agressivo).
1 ns _________ LETS SETUP A TIME/DISTANCE SCALE FIRST:
° ^
|\ |a 1 ft-distance a foton travels in vacuum ( less in dark-fibre )
| \ |
| \ |
__|___\__v____________________________________________________
| |
|<-->| a 1 ns TimeDOMAIN "distance", before a foton arrived
| |
^ v
DATA | |DATA
RQST'd| |RECV'd ( DATA XFER/FETCH latency )
25 ns @ 1147 MHz FERMI: GPU Streaming Multiprocessor REGISTER access
35 ns @ 1147 MHz FERMI: GPU Streaming Multiprocessor L1-onHit-[--8kB]CACHE
70 ns @ 1147 MHz FERMI: GPU Streaming Multiprocessor SHARED-MEM access
230 ns @ 1147 MHz FERMI: GPU Streaming Multiprocessor texL1-onHit-[--5kB]CACHE
320 ns @ 1147 MHz FERMI: GPU Streaming Multiprocessor texL2-onHit-[256kB]CACHE
350 ns
700 ns @ 1147 MHz FERMI: GPU Streaming Multiprocessor GLOBAL-MEM access
- - - - -
Portanto, entender as internalidades é muito mais importante do que em outros campos, onde as arquiteturas são publicadas e vários benchmarks disponíveis gratuitamente. Muito obrigado aos microtestadores de GPU, que gastaram seu tempo e criatividade para revelar a verdade dos verdadeiros esquemas de trabalho dentro da abordagem de caixa preta dos dispositivos de GPU testados.
+====================| + 11-12 [usec] XFER-LATENCY-up HostToDevice ~~~ same as Intel X48 / nForce 790i
| |||||||||||||||||| + 10-11 [usec] XFER-LATENCY-down DeviceToHost
| |||||||||||||||||| ~ 5.5 GB/sec XFER-BW-up ~~~ same as DDR2/DDR3 throughput
| |||||||||||||||||| ~ 5.2 GB/sec XFER-BW-down @8192 KB TEST-LOAD ( immune to attempts to OverClock PCIe_BUS_CLK 100-105-110-115 [MHz] ) [D:4.9.3]
|
| Host-side
| cudaHostRegister( void *ptr, size_t size, unsigned int flags )
| | +-------------- cudaHostRegisterPortable -- marks memory as PINNED MEMORY for all CUDA Contexts, not just the one, current, when the allocation was performed
| ___HostAllocWriteCombined_MEM / cudaHostFree() +---------------- cudaHostRegisterMapped -- maps memory allocation into the CUDA address space ( the Device pointer can be obtained by a call to cudaHostGetDevicePointer( void **pDevice, void *pHost, unsigned int flags=0 ); )
| ___HostRegisterPORTABLE___MEM / cudaHostUnregister( void *ptr )
| ||||||||||||||||||
| ||||||||||||||||||
| | PCIe-2.0 ( 4x) | ~ 4 GB/s over 4-Lanes ( PORT #2 )
| | PCIe-2.0 ( 8x) | ~16 GB/s over 8-Lanes
| | PCIe-2.0 (16x) | ~32 GB/s over 16-Lanes ( mode 16x )
|
| + PCIe-3.0 25-port 97-lanes non-blocking SwitchFabric ... +over copper/fiber
| ~~~ The latest PCIe specification, Gen 3, runs at 8Gbps per serial lane, enabling a 48-lane switch to handle a whopping 96 GBytes/sec. of full duplex peer to peer traffic. [I:]
|
| ~810 [ns] + InRam-"Network" / many-to-many parallel CPU/Memory "message" passing with less than 810 ns latency any-to-any
|
| ||||||||||||||||||
| ||||||||||||||||||
+====================|
|.pci............HOST|
Peço desculpas por uma "imagem maior", mas o excesso de latência também tem limites cardinais impostos pelas capacidades smREG / L1 / L2 e taxas de acerto / erro do chip.
|.pci............GPU.|
| | FERMI [GPU-CLK] ~ 0.9 [ns] but THE I/O LATENCIES PAR -- ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||| <800> warps ~~ 24000 + 3200 threads ~~ 27200 threads [!!]
| ^^^^^^^^|~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [!!]
| smREGs________________________________________ penalty +400 ~ +800 [GPU_CLKs] latency ( maskable by 400~800 WARPs ) on <Compile-time>-designed spillover(s) to locMEM__
| +350 ~ +700 [ns] @1147 MHz FERMI ^^^^^^^^
| | ^^^^^^^^
| +5 [ns] @ 200 MHz FPGA. . . . . . Xilinx/Zync Z7020/FPGA massive-parallel streamline-computing mode ev. PicoBlazer softCPU
| | ^^^^^^^^
| ~ +20 [ns] @1147 MHz FERMI ^^^^^^^^
| SM-REGISTERs/thread: max 63 for CC-2.x -with only about +22 [GPU_CLKs] latency ( maskable by 22-WARPs ) to hide on [REGISTER DEPENDENCY] when arithmetic result is to be served from previous [INSTR] [G]:10.4, Page-46
| max 63 for CC-3.0 - about +11 [GPU_CLKs] latency ( maskable by 44-WARPs ) [B]:5.2.3, Page-73
| max 128 for CC-1.x PAR -- ||||||||~~~|
| max 255 for CC-3.5 PAR -- ||||||||||||||||||~~~~~~|
|
| smREGs___BW ANALYZE REAL USE-PATTERNs IN PTX-creation PHASE << -Xptxas -v || nvcc -maxrregcount ( w|w/o spillover(s) )
| with about 8.0 TB/s BW [C:Pg.46]
| 1.3 TB/s BW shaMEM___ 4B * 32banks * 15 SMs * half 1.4GHz = 1.3 TB/s only on FERMI
| 0.1 TB/s BW gloMEM___
| ________________________________________________________________________________________________________________________________________________________________________________________________________________________
+========| DEVICE:3 PERSISTENT gloMEM___
| _|______________________________________________________________________________________________________________________________________________________________________________________________________________________
+======| DEVICE:2 PERSISTENT gloMEM___
| _|______________________________________________________________________________________________________________________________________________________________________________________________________________________
+====| DEVICE:1 PERSISTENT gloMEM___
| _|______________________________________________________________________________________________________________________________________________________________________________________________________________________
+==| DEVICE:0 PERSISTENT gloMEM_____________________________________________________________________+440 [GPU_CLKs]_________________________________________________________________________|_GB|
! | |\ + |
o | texMEM___|_\___________________________________texMEM______________________+_______________________________________________________________________________________|_MB|
| |\ \ |\ + |\ |
| texL2cache_| \ \ .| \_ _ _ _ _ _ _ _texL2cache +370 [GPU_CLKs] _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ | \ 256_KB|
| | \ \ | \ + |\ ^ \ |
| | \ \ | \ + | \ ^ \ |
| | \ \ | \ + | \ ^ \ |
| texL1cache_| \ \ .| \_ _ _ _ _ _texL1cache +260 [GPU_CLKs] _ _ _ _ _ _ _ _ _ | \_ _ _ _ _^ \ 5_KB|
| | \ \ | \ + ^\ ^ \ ^\ \ |
| shaMEM + conL3cache_| \ \ | \ _ _ _ _ conL3cache +220 [GPU_CLKs] ^ \ ^ \ ^ \ \ 32_KB|
| | \ \ | \ ^\ + ^ \ ^ \ ^ \ \ |
| | \ \ | \ ^ \ + ^ \ ^ \ ^ \ \ |
| ______________________|__________\_\_______________________|__________\_____^__\________+__________________________________________\_________\_____\________________________________|
| +220 [GPU-CLKs]_| |_ _ _ ___|\ \ \_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ \ _ _ _ _\_ _ _ _+220 [GPU_CLKs] on re-use at some +50 GPU_CLKs _IF_ a FETCH from yet-in-shaL2cache
| L2-on-re-use-only +80 [GPU-CLKs]_| 64 KB L2_|_ _ _ __|\\ \ \_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ \ _ _ _ _\_ _ _ + 80 [GPU_CLKs] on re-use from L1-cached (HIT) _IF_ a FETCH from yet-in-shaL1cache
| L1-on-re-use-only +40 [GPU-CLKs]_| 8 KB L1_|_ _ _ _|\\\ \_\__________________________________\________\_____+ 40 [GPU_CLKs]_____________________________________________________________________________|
| L1-on-re-use-only + 8 [GPU-CLKs]_| 2 KB L1_|__________|\\\\__________\_\__________________________________\________\____+ 8 [GPU_CLKs]_________________________________________________________conL1cache 2_KB|
| on-chip|smREG +22 [GPU-CLKs]_| |t[0_______^:~~~~~~~~~~~~~~~~\:________]
|CC- MAX |_|_|_|_|_|_|_|_|_|_|_| |t[1_______^ :________]
|2.x 63 |_|_|_|_|_|_|_|_|_|_|_| |t[2_______^ :________]
|1.x 128 |_|_|_|_|_|_|_|_|_|_|_| |t[3_______^ :________]
|3.5 255 REGISTERs|_|_|_|_|_|_|_|_| |t[4_______^ :________]
| per|_|_|_|_|_|_|_|_|_|_|_| |t[5_______^ :________]
| Thread_|_|_|_|_|_|_|_|_|_| |t[6_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| |t[7_______^ 1stHalf-WARP :________]______________
| |_|_|_|_|_|_|_|_|_|_|_| |t[ 8_______^:~~~~~~~~~~~~~~~~~:________]
| |_|_|_|_|_|_|_|_|_|_|_| |t[ 9_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| |t[ A_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| |t[ B_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| |t[ C_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| |t[ D_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| |t[ E_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| W0..|t[ F_______^____________WARP__:________]_____________
| |_|_|_|_|_|_|_|_|_|_|_| ..............
| |_|_|_|_|_|_|_|_|_|_|_| ............|t[0_______^:~~~~~~~~~~~~~~~\:________]
| |_|_|_|_|_|_|_|_|_|_|_| ............|t[1_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ............|t[2_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ............|t[3_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ............|t[4_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ............|t[5_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ............|t[6_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ............|t[7_______^ 1stHalf-WARP :________]______________
| |_|_|_|_|_|_|_|_|_|_|_| ............|t[ 8_______^:~~~~~~~~~~~~~~~~:________]
| |_|_|_|_|_|_|_|_|_|_|_| ............|t[ 9_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ............|t[ A_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ............|t[ B_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ............|t[ C_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ............|t[ D_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ............|t[ E_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| W1..............|t[ F_______^___________WARP__:________]_____________
| |_|_|_|_|_|_|_|_|_|_|_| ....................................................
| |_|_|_|_|_|_|_|_|_|_|_| ...................................................|t[0_______^:~~~~~~~~~~~~~~~\:________]
| |_|_|_|_|_|_|_|_|_|_|_| ...................................................|t[1_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ...................................................|t[2_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ...................................................|t[3_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ...................................................|t[4_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ...................................................|t[5_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ...................................................|t[6_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ...................................................|t[7_______^ 1stHalf-WARP :________]______________
| |_|_|_|_|_|_|_|_|_|_|_| ...................................................|t[ 8_______^:~~~~~~~~~~~~~~~~:________]
| |_|_|_|_|_|_|_|_|_|_|_| ...................................................|t[ 9_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ...................................................|t[ A_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ...................................................|t[ B_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ...................................................|t[ C_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ...................................................|t[ D_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_| ...................................................|t[ E_______^ :________]
| |_|_|_|_|_|_|_|_|_|_|_|tBlock Wn....................................................|t[ F_______^___________WARP__:________]_____________
|
| ________________ °°°°°°°°°°°°°°°°°°°°°°°°°°~~~~~~~~~~°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°
| / \ CC-2.0|||||||||||||||||||||||||| ~masked ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| / \ 1.hW ^|^|^|^|^|^|^|^|^|^|^|^|^| <wait>-s ^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|
| / \ 2.hW |^|^|^|^|^|^|^|^|^|^|^|^|^ |^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^|^
|_______________/ \______I|I|I|I|I|I|I|I|I|I|I|I|I|~~~~~~~~~~I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|I|
|~~~~~~~~~~~~~~/ SM:0.warpScheduler /~~~~~~~I~I~I~I~I~I~I~I~I~I~I~I~I~~~~~~~~~~~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I~I
| \ | //
| \ RR-mode //
| \ GREEDY-mode //
| \________________//
| \______________/SM:0__________________________________________________________________________________
| | |t[ F_______^___________WARP__:________]_______
| ..|SM:1__________________________________________________________________________________
| | |t[ F_______^___________WARP__:________]_______
| ..|SM:2__________________________________________________________________________________
| | |t[ F_______^___________WARP__:________]_______
| ..|SM:3__________________________________________________________________________________
| | |t[ F_______^___________WARP__:________]_______
| ..|SM:4__________________________________________________________________________________
| | |t[ F_______^___________WARP__:________]_______
| ..|SM:5__________________________________________________________________________________
| | |t[ F_______^___________WARP__:________]_______
| ..|SM:6__________________________________________________________________________________
| | |t[ F_______^___________WARP__:________]_______
| ..|SM:7__________________________________________________________________________________
| | |t[ F_______^___________WARP__:________]_______
| ..|SM:8__________________________________________________________________________________
| | |t[ F_______^___________WARP__:________]_______
| ..|SM:9__________________________________________________________________________________
| ..|SM:A |t[ F_______^___________WARP__:________]_______
| ..|SM:B |t[ F_______^___________WARP__:________]_______
| ..|SM:C |t[ F_______^___________WARP__:________]_______
| ..|SM:D |t[ F_______^___________WARP__:________]_______
| |_______________________________________________________________________________________
*/
A linha inferior?
Qualquer projeto motivado por baixa latência precisa fazer engenharia reversa da "hidráulica de E / S" (como 0 1-XFERs são incompressíveis por natureza) e as latências resultantes governam o envelope de desempenho para qualquer solução de GPGPU, seja intensivamente computacional ( leia-se : onde os custos de processamento estão perdoando um pouco mais os XFERs de baixa latência ...) ou não ( leia-se : (onde pode ser a surpresa de alguém) Os CPU-s são mais rápidos no processamento de ponta a ponta do que os tecidos GPU [citações disponíveis] )
