Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTAU (vector, 2S)

Test 1: uops

Code:

  fcvtau v0.2s, v0.2s
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303724426125472510001000100039816013018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
1004303723546125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372336125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037241266125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723276125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037232706125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037232586125472510001000100039816013018303730372414328951000100010003037303711100110000073116112699100030383038303830383038
10043037232316125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037242556125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtau v0.2s, v0.2s
  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)030b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037241000000612954725101001001000010010000500427716003001830037300372826432874510734200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
10204300372250000007262954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003722500016500612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003722500000080029547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000799116122963341100001003066130645306573071530656
10204306582381131317161056077842942926610253157100961351195082542941311304503066030610282923287451010024411988242123173065930714161102011009910010010000100220003898071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
10204300372250000006022954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300781110201100991001001000010000000071011611296330100001003003830228300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e3f4e51inst 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)696d6edispatch 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)9fa6a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
10024300372250061295473610010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000835406402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000306402162229629010000103003830038300383003830038
100243003722500536295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500726295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500536295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722510726295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtau v0.2s, v8.2s
  fcvtau v1.2s, v8.2s
  fcvtau v2.2s, v8.2s
  fcvtau v3.2s, v8.2s
  fcvtau v4.2s, v8.2s
  fcvtau v5.2s, v8.2s
  fcvtau v6.2s, v8.2s
  fcvtau v7.2s, v8.2s
  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)03070a1e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420069155000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039155110302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
80204200391561112302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039155110572580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181162120036800001002004020040200402004020040
8020420039155110302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
802042003915511018152580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039155000582580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000311151181161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e3f51inst 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)696d6edispatch 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)9fa8accdcfd0d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511560124025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000502006164420036080000102004020040200402004020040
80024200391550040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000101151502004164220036080000102004020040200402004020040
80024200391550082258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020122162420036080000102004020040200402004020040
8002420039155004025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000502004162520036080000102004020040200402004020040
8002420039155004025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000502034164420036080000102004020040200402004020040
8002420039156004025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000502035165420036080000102004020040200402004020040
80024200391550040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020164165420036080000102004020040200402004020040
8002420039155064025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000502002162420036080000102004020040200402004020040
8002420039155004025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010100502004165220036080000102004020040200402004020040
8002420039156004025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000503605165220036080000102004020040200402004020040