Apple Microarchitecture Research by Dougall Johnson

M1/A14 P-core (Firestorm): Overview | Base Instructions | SIMD and FP Instructions
M1/A14 E-core (Icestorm):  Overview | Base Instructions | SIMD and FP Instructions

ST1 (single, post-index, D)

Test 1: uops

Code:

  st1 { v0.d }[1], [x6], x8
  nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop
  mov x0, 0
  mov x8, 0

(no loop instructions)

1000 unrolls and 1 iteration

Retires (minus 60 nops): 2.000

Issues: 3.000

Integer unit issues: 1.000

Load/store unit issues: 1.000

SIMD/FP unit issues: 1.000

retire uop (01)cycle (02)03l1d tlb fill (05)mmu table walk instruction (07)mmu table walk data (08)09l2 tlb miss instruction (0a)l2 tlb miss data (0b)18191e1f223a3f464951schedule uop (52)schedule int uop (53)schedule simd uop (54)schedule ldst uop (55)dispatch int uop (56)dispatch simd uop (57)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)ldst uops in schedulers (5b)5f696d6emap rewind (75)map stall (76)dispatch uop (78)map ldst uop (7d)map simd uop (7e)map ldst uop inputs (80)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst simd store (99)inst ldst (9b)l1d tlb access (a0)l1d tlb miss (a1)l1d cache miss st (a2)ld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)a9acafbcl1d cache miss st nonspec (c0)l1d tlb miss nonspec (c1)c2c9cfd0d2l1i cache miss demand (d3)l1i tlb miss demand (d4)d5map dispatch bubble (d6)d9dadbddfetch restart (de)e0? int output thing (e9)eaebec? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
62006293202291910110000004477293481018315300010001000100010001000100050001090780009217092894829380310300010001000300010002938029394116100110001000100414110010011000130001307993116892307465120856318838121943462857710001628813480146091000100010002946029334294592934829271
62004292862280900700001045852910601184863000100010001000100010001000500010908800010217232896429472310300010001000300010002931129207116100110001000100223210010111000141101317193126960310554320698322438191646462865010001629713332142681000100010002925829203291962935129344
620042935622611011101000104667289880018291300010001000100010001000100050001090380008217252890629416310300010001000300010002922329315116100110001000100210110010111000130001313693366990306665120726316438141848432856810001587313362145601000100010002922929294292942938529293
62004293462271910131000104663291280018308300010001000100010001000100050001090980006216832896729398310300010001000300010002929429289116100110001000100214110010111000031001297192496848310044420701310738132244422857410001614713211145761000100010002927729274293192919229271
6200429284228090090000004516291400018326300010001000100010001000100050001089980009217192896129340310300010001000300010002919329326116100110001000100310010010111000130001294391646866311854920690326238171845462857710001620613404146211000100010002924829419293392938429264
620042940622708009000240044672920300183173000100010001000100010001000500010907800011216812894529344310300010001000300010002928129303116100110001000100220010010041000001001298891386852316264720681318238132349452862010001641313440145201000100010002935929333293522938729334
62004293412271801810001045982910500182973000100010001000100010001000500010904800012217602899829386310300010001000300010002924829194116100110001000100223110011111000100001317291636907313435020687322838201552452851610001648613333146651000100010002924929477293392943529379
6200429272227013001400001047282918910183723000100010001000100010001000500010907800010217192903329235310300010001000300010002920829284116100110001000100333010010011000131101310095116905311334620791325438192143422855410001637013382145101000100010002924229307293282933129307
62004293332270810100000004700291390018376300010001000100010001000100050001090280007216452906329294310300010001000300010002933629244116100110001000100213110010141000100001312894906826315434620743317738181345412854110001609213260146171000100010002931729376294352923029251
62004293402280900700000045492908611182633000100010001000100010001000500010907800011216572893429342310300010001000300010002917329211116100110001000100223110010141000031001324094376895306364820837313738221942442851210021638013366143111000100010002923929332293362935929235

Test 2: throughput

Count: 8

Code:

  st1 { v0.d }[1], [x6], x8
  st1 { v0.d }[1], [x6], x8
  st1 { v0.d }[1], [x6], x8
  st1 { v0.d }[1], [x6], x8
  st1 { v0.d }[1], [x6], x8
  st1 { v0.d }[1], [x6], x8
  st1 { v0.d }[1], [x6], x8
  st1 { v0.d }[1], [x6], x8
  mov x7, x6
  mov x8, x6
  mov x9, x6
  mov x10, x6
  mov x11, x6
  mov x12, x6
  mov x13, x6
  mov x8, 0

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 1.0005

retire uop (01)cycle (02)03l1d tlb fill (05)mmu table walk data (08)09l2 tlb miss data (0b)18191e1f22243a3f46494f51schedule uop (52)schedule int uop (53)schedule simd uop (54)schedule ldst uop (55)dispatch int uop (56)dispatch simd uop (57)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map ldst uop (7d)map simd uop (7e)map int uop inputs (7f)map ldst uop inputs (80)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd store (99)inst ldst (9b)9fl1d tlb access (a0)l1d tlb miss (a1)l1d cache miss st (a2)a4ld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)a9acafbcl1d cache miss st nonspec (c0)l1d tlb miss nonspec (c1)c2branch cond mispred nonspec (c5)branch mispred nonspec (cb)cdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
1602068004062100000012300080025081252401008010080000800008010080000800004359014375884864000018001580040800405992435999824010020080000800002002400008000080040800401180201100991001008000080000100800000170080001002800011170000051101161280037800008000080000801008004180041800418004180041
1602048004062000000012200080025881252401008010080000800008010080000800004359014375884864000018001580040800405992435999824010020080000800002002400008000080040800401180201100991001008000080000100800000170080001004800011170000051101161180037800008000080000801008004180041800418004180041
160204800406200000000210080152880252401008010080000800008010080000800004359014375884864000008001580040800405992435999824010020080000800002002400008000080040800401180201100991001008000080000100800000170080001005800011170000051102161280037800008000080000801008004180041800418004180041
16020480040621000000030008002580294252406398010080000800008010080000800004359014375884864000018001580040800405992435999824010020080120800002002400008000080040800401180201100991001008000080000100800000170080001001800611170000051102161180037800008000080000801008004180041800418004180041
16020480040620000000030008002588325240100801008000080000801008000080000435901437588486400000800158004080040599243599982401002008000080000200240000800008004080040118020110099100100800008000010080000000080000102800010170000051102162180037800008000080000801008004180041800418004180041
16020480040620000000132010080025881252401008010080000800008010080000800004359014375884864000018001580040800405992435999824010020080000801202002400008000080040800401180201100991001008000080000100800000190080001101800011170000051101162180142800008000080000801008004180041800418004180041
160204800406210000000300080025881252401008010080000800008010080000800004359014375884864000008001580040800405992435999824010020080000800002002400008000080040800401180201100991001008000080000100800000170080001101800011170000051102161280037800008000080000801008004180041800418004180041
16020480040620000000132200080025801252401008010080000800008010080000800004359014375884864000008001580040800405992435999824010020080000800002002400008000080040800401180201100991001008000080000100800000170080001002800011257100051102161280037800008000080000801008004180162800418004180041
160204800406201001000900180025111112524010080100800008000080100800008000043613933758848640000180015800408004059924359998240100200800008000020024000080000800408004011802011009910010080000800001008006782500800080114800018257100051101161280037800908000080000801008004180041800418004180041
16020480164620101000020008002588125240100801008000080000801008000080000435901437588486400000800158004080040599243599982401002008000080000200240000800008004080040118020110099100100800008000010080000017008000100280000000000051101161280037800008000080000801008004180164800418004180041

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 1.0005

retire uop (01)cycle (02)03l1d tlb fill (05)mmu table walk instruction (07)mmu table walk data (08)09l2 tlb miss instruction (0a)l2 tlb miss data (0b)18191e1f22243a3f46494f51schedule uop (52)schedule int uop (53)schedule simd uop (54)schedule ldst uop (55)dispatch int uop (56)dispatch simd uop (57)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)ldst uops in schedulers (5b)696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map ldst uop (7d)map simd uop (7e)map int uop inputs (7f)map ldst uop inputs (80)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd store (99)inst ldst (9b)9fl1d tlb access (a0)l1d tlb miss (a1)l1d cache miss st (a2)a4ld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)a9acafbcl1d cache miss st nonspec (c0)l1d tlb miss nonspec (c1)c2cfd2d5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
16002680040621000000005731008002508353240010800108000080000800108000080108435842937588486400008001580162800405994636002024001020800008000020240000800008004080040118002110910108000080000108000001700800010028000111700504003163580037800008000080000800108004180041800418004180041
160024800406210000000031220008002588325240010800108000080000800108000080000435842937588486400008001580040800405994636002024035020800008000020240000800008004080040118002110910108000080000108000001700800000028000111700502004165380037800008000080000800108016480041800418004180041
16002480040621000000004713000800250822524001080010800008000080010800008000043584293758848640000800158004080040599463600202400102080000800002024000080000800408004011800211091010800008000010800000000800010028000111700502003165480037800008000080000800108004180161800418004180041
16002480040620000000003573000800258032524001080010800008000080010800008000043608283758848640000800158004080040599463600202400102080000800002024000080000800408004011800211091010800008000010800000170080000001800011170250207524164480141800008000080000800108004180041801618004180041
16002480040620100000000900180025001252400108010080000800008001080000800004358409375884864000080015800408004059946360020240010208000080000202400008012080040800401180021109101080000800001080000729008000800118006112100502006165380037800008000080000800108004180041800418004180041
1600248004062000000000211200180025882252400108001080000800008001080000800004358429375884864000080015800408004059946360020240350208000080000202400008000080040800401180021109101080000800001080000021028000110118000102100502003163480037800928000080000800108004180041800418004180041
16002480040621000000102720008002500325240010800108000080000800108000080000435840537588486400008001580040800405994636002024001020800008000020240000800008004080040118002110910108000080000108006782900800080018000182100502004165380037800008000080000800108004180041800418004180041
160024800406211000000025290008014790225240010800108000080000800108000080000435842937588486400008001580040800405994636002024001020800008000020240000800008004080040118002110910108000080000108000000008000800118006182971502003164480037800008000080000800108004180041800418004180041
160024800406201000000021970018002588525240010800108000080000800108000080000435840537588486400008001580040800405994636002024001020800008000020240000800008004080040118002110910108000080000108000792100800610018000112100502005163280037800008000080000800108004180041800418004180041
160024800406200000001090000800250012524001080010800008006080010800008000043584093758848640000800158004080040599463600202400102080000800002024000080120800408004011800211091010800008000010800077000800080068000182970502003163580037800008000080000800108004180041800418004180041