Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTA (scalar, S)

Test 1: uops

Code:

  frinta s0, s0
  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)696d6edispatch 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)a0a1a6cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372496125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112699100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100001073116112664100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372406125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372436125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frinta s0, s0
  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)03080b18191e1f3a3f4e51inst 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)9fa0a1a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300000002225295294510136110100161291015059742793870300903008430084282697287631026620610327208103333008430120311020110099100100100001000030040710116122966900100001003013430089300383003830038
1020430037233000000145412947517410198147100561171105071542866240302703037030374283003928873111902201115522611156303703018081102011009910010010000100021022109207781751129938350100001003056130612305543055630562
1020430559234111011145296808101294482271024415410032160115007954283920030234306003056328296532894911137235118212141182830550305591211020110099100100100001002232386900098221282430029160100001003054830515302313061430601
1020430598237101111159396808539294842591025916510088155115237804293384030450305633056028302552893211805246118182381180430561305651211020110099100100100001004220306450096511051130086250100001003061430564304213056030326
10204302762360101000612954725101001001000010010000500427716003001830037300372826432874510422200100002001000030037300371110201100991001001000010000170600710116112963300100001003003830038300383003830038
10204300372320000000612954725101001001000013710000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000160000710116112963300100001003003830038300383003830038
10204300372320000000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000220600710116112963300100001003003830038300383003830038
102043003723200000002012954725101001001000010010000500427716003001830037300372826432874510100200100002001018030037300371110201100991001001000010000180900710116112963300100001003003830038300383003830038
10204300372330000000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000300000710116112963300100001003003830038300383003830038
10204300372320000000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000210300710116112963300100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080b18191e1f3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
1002430037234301000099942943026410119141009615112007142906800302703056130605283483428972118152412144221129630655306491011002110910101000010037985085221214229667010000103040530424302743041730558
100243035823501110710597922852954725100101010008101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010015906402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001001677626402162229629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722400000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722400000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830071
100243003722500000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frinta s0, s8
  frinta s1, s8
  frinta s2, s8
  frinta s3, s8
  frinta s4, s8
  frinta s5, s8
  frinta s6, s8
  frinta s7, s8
  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)03090b18191e1f3a3f51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815500000001182580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801610200360800001002004020040200402004020040
80204200391550000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001000111511801610200360800001002004020040200402004020040
802042003915500000007425801081008000810080020500640132120020200392003999771099908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
80204200391560000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801610200360800001002004020040200402004020040
80204200391550000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
80204200391560000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
80204200391550000282003342580108100800081008002050064013212002020039202489977699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
802042003915500100006402580108100800081008002050064013212002020039200399977699908012020080032200800322008920039118020110099100100800001000000000111511801610200360800001002004020040200402004020040
802042003915500001200722580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801601200360800001002004020040200912004020040
80204200391610000000302580108100800081008002050064013212002020039200399977699908012020080032200801442003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040

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)5f60696d6edispatch 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)9fa8acc2c5cfd2d5d6dadbddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391550006125800101080000108000050640000012002020039200399996031001980010208000020800002003920039118002110910108000010000050380616005320036080000102004020040200402004020040
80024200391550004025800101080000108000050640000112002020039200399996031001980010208000020800002003920039118002110910108000010000050200316005620036080000102004020040200402004020040
800242003915600012625800101080000108000050640000112002020039200399996031001980010208000020800002003920039118002110910108000010000050200316003520036080000102004020040200402004020040
80024200391550004025800101080000108000050640000002002020039200399996031001980010208000020800002003920039118002110910108000010000050200316006620036080000102004020040200402004020040
800242003915500092725800101080000108000050640000002002020039200399996031001980010208000020800002003920039118002110910108000010000050200316005320036080000102004020040200402004020040
80024200391550004025800101080000108000050640000002002020039200399996031001980010208000020800002003920039118002110910108000010000050200516005320036080000102004020040200402004020040
800242003915500017425800101080000108000050640000012002020039200399996071001980010208000020800002003920039118002110910108000010000050200616006320036080000102004020040200402004020040
80024200391550004025800101080000108000050640000012002020039200399996031001980010208000020800002003920039118002110910108000010000050200616003620036080000102004020040200402004020040
800242003915500013025800101080000108000050640000002002020039200399996031001980010208000020800002003920039118002110910108000010000050200316003520036080000102004020040200402004020040
80024200391550004025800101080000108000050640000012002020039200399996031001980010208000020800002003920039118002110910108000010030050200516006620036080000102004020040200402004020040