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, 2D)

Test 1: uops

Code:

  fcvtau v0.2d, v0.2d
  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)0307080a1e3a3f4e51inst 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
1004303723101026925472510001000100039816013018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
10043037241010211125472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
10043037241010269254725100010001000398160030183037303724143289510001000100030373037111001100019077416442629100030383038303830383038
1004303723101026925472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383085
10043037231011226925472510001000100039816003018303730372414328951000100010003037303711100110000377416442629100030383184303830383038
1004303724101026925472510001000100039816013018303730372414328951000100010003037303711100110000377416442629100030383038303830383038
10043037241011226925472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
1004303723101026925472510001000100039816013018303730372414328951000100010003037303711100110000677416442629100030383038303830383038
1004303724101026925472510001000100039816013018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
1004303724101026925472510001000100039816013018303730372414328951000100010003037303711100110001377416442629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtau v0.2d, v0.2d
  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)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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd0d5d6daddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300000006129547251010010010000100100005004277160030018300373003728264032874510100200100002001000030037300371110201100991001001000010000000000007100216022296330100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160030018300373003728264032874510100200100002001000030037300371110201100991001001000010000000000007100216022296330100001003003830038300383003830038
102043003723200000006129547251010010010000100100005004277160030018300373003728264032874510100200100002001000030037300371110201100991001001000010000010000007100216022296330100001003003830038300383003830038
10204300372330000000199629547251010010010000100100005004277160030018300373003728264032874510100200100002001000030037300371110201100991001001000010000000000007100216022296330100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160030018300373003728264032874510100200100002001000030037300371110201100991001001000010000000000007100216022296330100001003003830038300383003830038
102043003723200000006129547251010010010000100100005004277160030018300373003728264032874510100200100002001000030037300371110201100991001001000010000000000007105216022296330100001003003830038300383003830038
102043003723200000006129547251010010010000100100005004277160030018300373003728264032874510100200100002001000030037300371110201100991001001000010000000000007100216022296330100001003003830038300383003830038
1020430037232000000034629547251010010010000100100005004277160030018300373003728264032874510100200100002001000030037300371110201100991001001000010000000000007100216022296330100001003003830038300383003830038
1020430037233000000025729547251010010010000100100005004277160030018300373003728271762874010100200100082001000830037300371110201100991001001000010000000001117170116011296450100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160030018300373003728271062874110100200100082001000830037300371110201100991001001000010000000000007100216022296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243036924411691584792952029511191100801610037141075094428797603001830037300372828632876710010201033420100003018130084411002110910101000010000640216222962910000103003830038300383003830038
1002430037241000000171295472510010101000010100005042771603103001830037300372828632876710010201000020100003003730037111002110910101000010100640217222962910000103003830038300383003830038
100243003724100003010329547251001010100001010000504277160030018300373003728291862876710010201000020100003007130037111002210910101000010000640216222962910000103003830038300383003830083
1002430037241000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372330000001032954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010100640216222962910000103003830038300383003830038
1002430037233001100612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037233000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010030640216222962910000103003830038300383003830038
10024300372320000002652954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372330000001932954725100101010000101000050427716003001830037300372830632876710010201000020100003003730037111002110910101000010100640216222962910000103003830038300383003830038
10024300372320000001702954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtau v0.2d, v8.2d
  fcvtau v1.2d, v8.2d
  fcvtau v2.2d, v8.2d
  fcvtau v3.2d, v8.2d
  fcvtau v4.2d, v8.2d
  fcvtau v5.2d, v8.2d
  fcvtau v6.2d, v8.2d
  fcvtau v7.2d, v8.2d
  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)03080b1e3f51inst 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)9fa1a8acc2c5branch mispredict (cb)cdcfd6e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915500105302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816200360800001002004020040200402004020040
80204200391550024302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816200360800001002004020040200402004020040
8020420039155006302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816200360800001002004020040200402004020040
8020420039156000302580108100800081028002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816200360800001002004020040200402004020040
80204200391610012302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816200360800001002004020040200402004020040
8020420039156000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816200360800001002004020040200402004020040
8020420039155000362580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816200360800001002004020040200402004020040
8020420039161000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816200360800001002004020040200402004020040
802042003915600181252580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816200360800001002004020040200402004020040
8020420039155000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051155040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020416232003680000102004020040200402004020040
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020316322003680000102004020040200402004020040
8002420039155040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020316332003680000102004020040200402004020040
8002420039155040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005046316432003680000102004020040200402004020040
8002420039155040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020316332003680000102004020040200402004020040
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020216232003680000102004020040200402004020040
8002420039161040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020316322003680000102004020040200402004020040
80024200391550705258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020316342003680000102004020040200402004020040
8002420039156082258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020216342003680000102004020040200402004020040
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020316332003680000102004020040200402004020040