Year Micro-architecture Pipeline stages Max clock (MHz) Process node
1978 8086 (8086, 8088) 2 5 3000 nm
1982 186 (80186, 80188) 2 25
1982 286 (80286) 3 25 1500 nm
1985 386 (80386) 6[1] 33
1989 486 (80486) 5 100 1000 nm
1993 P5 (Pentium) 5 200 800, 600, 350 nm
1995 P6 (Pentium Pro, Pentium II) 14 (17 with load & store/retire) 450 500, 350, 250 nm
1997 P5 (Pentium MMX) 6 233 350 nm
1999 P6 (Pentium III) 12 (15 with load & store/retire) 1400 250, 180, 130 nm
2000 NetBurst (Pentium 4) (Willamette) 20 unified with branch prediction 2000 180 nm
2002 NetBurst (Pentium 4) (Northwood, Gallatin) 3466 130 nm
2003 Pentium M (Banias, Dothan) Enhanced Pentium M (Yonah) 10 (12 with fetch/retire) 2333 130, 90, 65 nm
2004 NetBurst (Pentium 4, Pentium D) (Prescott) 31 unified with branch prediction 3800 90, 65 nm
2006 Intel Core 12 (14 with fetch/retire) 3000 65 nm
2007 Penryn (die shrink) 3333 45 nm
2008 Nehalem 20 unified (14 without miss prediction) 3600
Bonnell 16 (20 with prediction miss) 2100
2010 Westmere (die shrink) 20 unified (14 without miss prediction) 3866 32 nm
2011 Saltwell (die shrink) 16 (20 with prediction miss) 2130
Sandy Bridge 14 (16 with fetch/retire) 4000
2012 Ivy Bridge (die shrink) 4100 22 nm
2013 Silvermont 14–17 (16–19 with fetch/retire) 2670
Haswell 14 (16 with fetch/retire) 4400
2014 Broadwell (die shrink) 3700 14 nm
2015 Airmont (die shrink) 14–17 (16–19 with fetch/retire) 2640
Skylake 14 (16 with fetch/retire) 5200
2016 Goldmont 20 unified with branch prediction 2600
2017 Goldmont Plus 20 unified with branch prediction (?) 2800
2018 Palm Cove 14 (16 with fetch/retire) 3200 10 nm
2019 Sunny Cove 14–20 (misprediction) 4100
2020 Tremont 20 unified 3300
Willow Cove 14 unified 5300
2021 Cypress Cove 14 unified 5300 14 nm
Golden Cove 12 unified 5500 Intel 7
Gracemont 20 unified with misprediction penalty 4300
2022 Raptor Cove 12 unified 5800
NOTE: ATOM/POWER EFFICIENT MICROARCHITECTURES ARE IN ITALIC