Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

SQNEG (vector, 8B)

Test 1: uops

Code:

  sqneg v0.8b, v0.8b
  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073216112629100030383038303830383038
1004303723082254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230105254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372315661254725100010001150398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037237261254725100010001000398160130183037303724143289510001000100030373037111001100000073116102629100030383038303830383038
10043037220156254725100010001000398160130183037303724143289510001000100030373037111001100000673116112629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038308630383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372334261254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqneg v0.8b, v0.8b
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318193a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a7a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000001071011611296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427761513001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000010071011611296330100001003003830084301813008530038
10204300372250004202954725101001001000010010000500427716013001830037300372826432874510100200100002041000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296332100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080a0b18191e1f3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing ld/st (5a)huge thing fp/simd (5b)60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250010000006129547251001010100001010000500427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372240000000006129547251001010100001010000500427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000006129547251001010100001010000500427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000006129547251001010100001010000500427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000019810806129547251001010100001010000500427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000006129547251001010100001010000500427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000006129547251001010100001010000500427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000006129547251001010100001010000500427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000306402162229629510000103037030321303703037030359
1002430414227201177924528014262948415410070141004810109656004285272030234030225303652831229288991029920111382211071303683017771100211091010100001022012194880817117271829881410000103041030369303673036830086
1002430369228612178121760822954725100101010000101000050042771600300180300373003728286328847110632210985221098330369300378110021109101010000104200219275281547311829881210000103037030368303563032330368

Test 3: throughput

Count: 8

Code:

  sqneg v0.8b, v8.8b
  sqneg v1.8b, v8.8b
  sqneg v2.8b, v8.8b
  sqneg v3.8b, v8.8b
  sqneg v4.8b, v8.8b
  sqneg v5.8b, v8.8b
  sqneg v6.8b, v8.8b
  sqneg v7.8b, v8.8b
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)030708191e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000000302580108100800081008002050064013212002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151181160020036800001002004020040200402004020040
8020420039150000210302580108100800081008002050064013212002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915000000302580108100800081008002050064013212002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
8020420039150000001412580108100800081008002050064013212002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391500000030258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010000013511151180160020036800001002004020040200402004020040
802042003915000030030258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010000020411151180160020036800001002004020040200402004020040
802042003915000000302580108100800081008002050064013202006420089200399977069990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391500000030258010810080008100800205006401320200202003920039997706999080120200800322008003220039200391180201100991001008000010000012911151180160020036800001002004020040200402004020040
802042003915000000302580108100800081008002050064013212002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
8020420039150000003025801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000007211151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)0318191e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f6061696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a6a8acc2branch mispredict (cb)cfd0d2d5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000040258001010800001080000506400000102002020039200399996310019800102080000208000020039200391180021109101080000100000005038006167520036080000102004020040200402004020196
800242003915000040258001010800001080310506400001102002020039200399996310046800102080319208000020039200393180021109101080000100401421005020005165720036080000102004020040200402004020040
800242004215000040258001010800001080000506400000102002020039200399996310019800102080000208000020039200391180021109101080000100000005020008168820036080000102004020040200402004020040
800242003915000040258001010800001080000506400000102002020039200399996310019800102080000208000020039200391180021109101080000100000005020006165620036080000102004020040200402004020040
800242003915000085258001010800001080000506400000102002020039200399996310019800102080000208000020039200391180021109101080000100000005020007165820036080000102004020040200402004020040
800242003915000640258001010800001080000506400000102002020039200399996310019800102080000208000020039200391180021109101080000100000005020007166820036080000102004020040200402004020040
800242003915600940258001010800001080000506400000102002020039200399996310019800102080000208000020039200391180021109101080000100000005020006166520036080000102004020040200402004020040
800242003915000040258001010800001080000506400000102002020039200399996310019800102080000208000020039200391180021109101080000100000005020007167520036080000102004020040200402004020040
800242003915000040258001010800001080000506400000102002020039200399996310019800102080000208000020039200391180021109101080000100000005020007168820036080000102004020040200402004020040
800242003915000040258001010800001080000506400000102002020039200399996310019800102080000208000020039200391180021109101080000100000005020008166720036080000102004020040200402004020040