Comparison of CPU microarchitectures

The following is a  comparison of CPU microarchitectures  .

microarchitecture Pipeline Internships Misc
AMD K5 Out-of-order execution , register, speculative execution
AMD K6 Superscalar , branch prediction
AMD K6-III Branch prediction , speculative execution , out-of-order execution  [1]
AMD K7 Out-of-order execution, prediction branch, Harvard architecture
AMD K8 64- bit , integrated memory controller, 16 byte prefetching instruction
AMD K10 Superscalar, out-of-order execution, 32-way associative set L3 victim cache , 32-byte prefetching statement
ARM810 5
ARM1020E 6
XScale PXA210 / PXA250 7
ARM1136J (F) -S 8
ARM1156T2 (F) -S 9
ARM Cortex-A5 8 Single issue, in-order
ARM Cortex-A7 MPCore 8 Partial dual-issue, in-order
ARM Cortex-A8 13 Dual-issue
ARM Cortex-A9 MPCore 8-11 Out-of-order, speculative issue, superscalar
ARM Cortex-A15 MPCore 15 Multi-core (up to 16), out-of-order, speculative issue, 3-way superscalar
ARM Cortex-A53 Partial dual-issue, in-order
ARM Cortex -A57 Deeply out-of-order, wide multi-issue, 3-way superscalar
ARM Cortex-A73 Out-of-order superscalar
ARM Cortex-A75 Out-of-order superscalar
AVR32 AP7 7
AVR32 UC3 3 Harvard architecture
Bobcat Out-of-order execution
Bulldozer Shared multithreaded L2 cache, multithreading, multi-core, around 20 stage long pipeline, integrated memory controller, out-of-order, superscalar, up to 16 cores per chip, up to 16 MB L3 cache, Virtualization, Turbo Core, FlexFPU which uses simultaneous multithreading  [2]
Piledriver Shared multithreaded L2 cache, multithreading, multi-core, around 20 stage long pipeline, integrated memory controller , out-of-order, superscalar, up to 16 MB L2 cache, up to 16 MB L3 cache, Virtualization, FlexFPU which use simultaneous multithreading ,  [2]  up to 16 cores per chip, up to 5 GHz clock speed, up to 220 W TDP, Turbo Core
Excavator 4
Zen 19 Superscalar, multithreading, 4-way decode, out-of-order execution
Crusoe In-order execution, 128-bit VLIW, integrated memory controller
Efficeon In-order execution, 256-bit VLIW, fully integrated memory controller
Cyrix Cx5x86 [3] Branch prediction
Cyrix 6×86 Superscalar, superpipelined, register renaming, speculative execution, out-of-order execution
eIf-3200 5 In-order, speculative issue
eIf-3250 5 In-order, speculative issue
EV4 (Alpha 21064) superscalar
EV7 (Alpha 21364) Superscalar design with out-of-order execution, branch prediction, 4-way simultaneous multithreading, integrated memory controller
EV8 (Alpha 21464) Superscalar design with out-of-order execution
65k 30+ Ultra low power consumption, register renaming, out of order execution, branch prediction, multi-core, module, capable of reach higher clock
P5 (Pentium) 5 superscalar
P6 ( Pentium Pro ) 14 Speculative execution, registering renaming, superscalar design with out-of-order execution
P6 ( Pentium II ) 14  [4] Branch prediction
P6 ( Pentium III ) 14  [4]
Intel Itanium 11  [5] Speculative execution , branch prediction , register renaming, 30 execution units , multithreading , multi-core , coarse-grained mutithreading, 2-way simultaneous multithreading , dual-domain multithreading, Turbo Boost , Virtualization , VLIW , SAR with Advanced Machine Check Architecture, Education Replay technology, Cache Safe technology, Enhanced SpeedStep technology
Intel NetBurst (Willamette ) 20 2-way simultaneous multithreading ( Hyper-Threading ), Rapid Execution Engine, Execution Trace Cache, Quad-pumped Front-Side Bus, Hyper-pipelined Technology, superscalar, out-of order
NetBurst (Northwood ) 20 2-way simultaneous multithreading
NetBurst ( Prescott) 31 2-way simultaneous multithreading
NetBurst ( Cedar Mill ) 31 2-way simultaneous multithreading
Intel Core 12 Multi-core, out-of-order, 4-way superscalar
Intel Atom 16 2-way simultaneous multithreading, in-order, no reordering instruction, speculative execution, or register renaming
Intel Atom Oak Trail 2-way simultaneous multithreading, in-order, mode burst, 512 KB L2 cache
Intel Atom Silvermont Out-of-order execution
Nehalem 14 2-way simultaneous multithreading, out-of-order, 6-way superscalar, integrated memory controller, L1 / L2 / L3 cache, Turbo Boost
Sandy Bridge 14 2-way simultaneous multi-threading, multi-core, on-die graphics and PCIe controllers, system controller with integrated memory and display controller, ring interconnect, L1 / L2 / L3 cache, micro-op cache, 2 threads per core, Turbo Boost,
Intel Haswell 14-19 SoC design, multi-core, multithreading, 2-way simultaneous multithreading, hardware-based transactional memory (in selected models), L4 cache (in GT3 models), Turbo Boost , out-of-order execution , superscalar , up to 8 MB L3 cache (mainstream), up to 20 MB L3 cache (Extreme)
Broadwell 14-19 Multi-core, multithreading
Skylake 14-19 Multi-core, L4 cache on some Skylake-R, Skylake-U and Skylake-Y models. On-package PCH on U, Y, m3, m5 and m7 models.
Kaby Lake 14-19 Multi-core, L4 cache on some low and ultra low power models (Kaby Lake-U and Kaby Lake-Y),
Intel Xeon Phi7120x 7-stage integer, 6-stage vector Multi-core, multithreading, 4 hardware-based simultaneous threads per core which can not be disabled unlike regular HyperThreading , Time-multiplexed multithreading, 61 cores per chip, 244 threads per chip, 30.5 MB L2 cache , 300 W TDP, Turbo Boost , in-order dual-issue pipelines, Coprocessor , Floating-Point Accelerator, 512-bit wide Vector -FPU
latticemico32 6 Harvard architecture
POWER1 Superscalar, out-of-order execution
POWER3 Superscalar, out-of-order execution
POWER4 Superscalar, speculative execution, out-of-order execution
POWER5 2-way simultaneous multi-threading, out-of-order execution, integrated memory controller
IBM POWER6 2-way simultaneous multithreading , in-order execution, up to 5 GHz
IBM POWER7 + Multi-core, multithreading, out-of-order, superscalar, 4 intelligent simultaneous threads per core, 12 execution units per core, 8 cores per chip, 80 MB L3 cache, true hardware entropy generator, hardware-assisted cryptographic acceleration, fixed- point unit, decimal fixed-point unit, Turbo Core, decimal floating-point unit
IBM Cell Multi-core, multithreading, 2-way simultaneous multithreading (PPE), Power Processor Element , Synergistic Element Processing, Element Interconnect Bus, in-order execution
IBM Cyclops64 Multi-core, multithreading, 2 threads per core, in-order
IBM zEnterprisezEC12 15/16/17 Multi-core, 6 cores per chip , up to 5.5 GHz , superscalar , out-of-order, 48 MB L3 cache, 384 MB shared L4 cache
IBM A2 15
PowerPC 401 3
PowerPC 405 5
PowerPC 440 7
PowerPC 470 9 Symmetric multiprocessing (SMP)
PowerPC e300 4 Superscalar, branch prediction
PowerPC e500 Dual 7 stage Multi-core
PowerPC e600 3-issue 7 stage Superscalar out-of-order execution, branch prediction
PowerPC e5500 4-issue 7 stage Out-of-order, multi-core
PowerPC e6500 Multi-core
PowerPC 603 4 5 execution units, branch prediction, no SMP
PowerPC 603q 5 In-order
PowerPC 604 6 Superscalar, out-of-order execution, 6 execution units, SMP support
PowerPC 620 5 Out-of-order execution, SMP support
PWRficient Superscalar, out-of-order execution, 6 execution units
R4000 8 Scalar
StrongARM SA-110 5 Scalar, in-order
SuperH SH2 5
SuperH SH2A 5 Superscalar, Harvard architecture
SPARC superscalar
hypersparc superscalar
SuperSPARC Superscalar, in-order
SPARC64 VI / VII / VII + Superscalar, out-of-order  [6]
UltraSPARC 9
UltraSPARC T1 6 Open source, multithreading, multi-core, 4 threads per core, integrated memory controller
UltraSPARC T2 8 Open source, multithreading, multi-core, 8 threads per core
SPARC T3 8 Multithreading, multi-core, 8 threads per core, SMP, 16 cores per chip, 2 MB L3 cache, in-order, hardware random generator
Oracle SPARC T4 16 Multithreading, multi-core, 8-threaded, 2-way simultaneous multithreading , SMP, 8-core per chip, out-of-order, 4 MB L3 cache, out-of order, Hardware random number generator
Oracle Corporation SPARC T5 16 Multithreading, multi-core , 8-bit multi-core , 2-way simultaneous multithreading , 16 cores per chip, out-of-order, shared 16-way shared 8 MB L3 cache, hardware- assisted cryptographic acceleration, stream-processing unit, out-of-order execution, RAS features, 16 cryptography units per chip, hardware random number generator
Oracle SPARC M5 16 Multithreading, multi-core, 8 fine-grained threads per core of which 2 can be executed simultaneously, 2-way simultaneous multithreading , 6 cores per chip, out-of-order, 48 MB L3 cache, out-of order execution, RAS features, stream-processing unit, Hardware-Assisted Cryptographic Acceleration, 6 Cryptography Units per Chip, Hardware random number generator
Fujitsu SPARC64 X Multithreading, multi-core, 2-way simultaneous multithreading, 16 cores per chip, out-of order, 24 MB L2 cache, out-of order, RAS features
Imagination Technologies MIPS Warrior
VIA C7 In-order execution
VIA Nano (Isaiah) Superscalar out-of-order execution, prediction branch, 7 execution units
WinChip 4 In-order execution

See also

  • CPU design
  • Comparison of instruction set architectures


  1. Jump up^  “Products We Design” . . Retrieved 19 January 2014 .
  2. ^ Jump up to: b   “wp-content / uploads / 2013/07 / AMD-Steamroller-vs-Bulldozer” . . Retrieved 19 January 2014 .
  3. Jump up^  “Cyrix 5×86 (” M1sc “)” . . Retrieved 19 January 2014 .
  4. ^ Jump up to: b   “Computer Science 246: Computer Architecture” (PDF) . Harvard University . Retrieved 23 December 2013 .  P6 pipeline
  5. Jump up^   Intel Itanium 2 Processor Hardware Developer’s Manual . p. 14. Retrieved 28 November 2011
  6. Jump up^  “Multi Core Processor SPARC64 ™ Series: Fujitsu Global” . . Retrieved 19 January 2014 .

Leave a Reply

Your email address will not be published. Required fields are marked *

Copyright 2019
Shale theme by Siteturner