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

LDR (unsigned offset, S)

Test 1: uops

Code:

  ldr s0, [x6, #8]
  mov x0, 1
  mov x1, 2
  mov x8, 0

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 1.000

SIMD/FP unit issues: 0.000

retire uop (01)cycle (02)03l1d tlb fill (05)mmu table walk data (08)09l2 tlb miss data (0b)0e0f1e22243a3f4346494f51schedule uop (52)schedule ldst uop (55)dispatch ldst uop (58)simd uops in schedulers (5a)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map ldst uop (7d)map ldst uop inputs (80)8283flush restart other nonspec (84)85inst all (8c)92inst simd load (98)inst ldst (9b)9dl1d tlb access (a0)l1d tlb miss (a1)l1d cache miss ld (a3)ld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)a9acafb5b6bbl1d cache miss ld nonspec (bf)l1d tlb miss nonspec (c1)c2cfd5map dispatch bubble (d6)ddfetch restart (de)e0eaebec? ldst retires (ed)f5f6f7f8fd
100540331100004510138801212162510001000100014989036937439421732521000100010003943741110010100010000101919431019100010006139000732162237101451000399401375399375
100437430000004410139001211625100010001000152670374398398224325610001000100039437411100101000100001019190107300021104060594519173216223950051000404404383409404
10043813100000670013880012025100010001000140601374398394221323210001000100039437411100161000100011000043100000038103800044007321622395101101000399375405399399
1004374300000100013880001925100010001000152670349398394221323210001000100039439411100101000100001019200106000161104061580191732162240013001000404404382403404
100440531100004510139030120251000100010001527403733983982213232100010001000396394111001010001000010000431039000381039613900073216223910041000400375400399399
10043773000000531013882001925100010001000160880373398374217325610001000100039839411100101000100001020204310581002110376104300732162239101351000404404404383383
100438131101110001398077125100010001000152740349374374197325610001000100039839411100101000100011000043103800038100001384400732162239501351000375376399375375
10043742000000461003872771925100010001000155080356403402225326010001000100039839411100101000100001000043103800001000613900073216223710071000399399375399399
100439830000004410038727719251000100010001531503493743742213232100010001000398394111001010001000010201901059101611041603900073216223710041000375375375375399
1004398300000044101388011162510001000100014989034937437422132561000100010003983941110010100010000102019441059101611040601943191732162240013051000404403404382404

Test 2: Latency 1->2 roundtrip

Chain cycles: 3

Code:

  ldr s0, [x6, #8]
  fmov x0, d0
  eor x8, x8, x0
  eor x8, x8, x0
  add x6, x6, x8
  mov x0, 1
  mov x1, 2
  mov x8, 0

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code, minus 3 chain cycles): 9.0074

retire uop (01)cycle (02)03l1d tlb fill (05)mmu table walk data (08)0e0f18191e2223243a3f4d4f51schedule 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 load (98)inst ldst (9b)9d9fl1d tlb access (a0)l1d tlb miss (a1)l1d cache miss ld (a3)ld unit uop (a6)l1d cache writeback (a8)a9acafb5bbl1d cache miss ld nonspec (bf)l1d tlb miss nonspec (c1)c2branch cond mispred nonspec (c5)branch mispred nonspec (cb)cfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)eaebec? ldst retires (ed)? int retires (ef)f5f6f7f8fd
50205120057899000100610001200201194931094672560103401021000010000301001000010000107886257363806136317112001112007712007111314631136685010030200100001000060200100001000012005112005411502011009910040100100001000011001000000100000001000010100003210110711119658400021310121000040100120055120055120055120055120055
5020412005189900010010000120039119513109467256010340102100011000030100100001000010790355735455613631701200111200941200531131493113671501003020010000100006020010000100001200351200351150201100991004010010000100000100100000110000003100001010000321011071111964640000131091000040100120036120036120055120052120055
502041200548990000006000012002011951010944925601034010010001100003010010000100001078862573623661363171120030120090120096113141311367150100302001000010000602001000010000120054120054115020110099100401001000010000010010000001000000010000001000032101107111196614000001301000040100120055120055120036120052120055
5020412005189900000010000120020119513109467256010040100100011000030100100001000010790355736380613446101200301201211200841131413113671501003020010000100006020010000100001200511200351150201100991004010010000100000100100000110000000100001010000321011071111964640000013121000040100120055120060120055120055120036
5020412005489900000010000012003911951310946725601034010010000100003010010000100001079035573638061363171120030120109120053113146311365850100302001000010000602001000010000120054120051115020110099100401001000010000010010000001000000010000101000032101107111196584000001391000040100120052120036120052120052120052
502041200548990000006000012003611951010946425601034010010001100003010010000100001079008573710161383920120030120108120069113149311375650100302001000010000602001000010000120035120035115020110099100401001000010000010010000001000000010000101040032101107111196624000201001000040100120036120052120036120052120055
5020412005189900000010000120022119513109449256010340102100011000030100100001000010790355735455613446101200271200811200591131493113668501003020010000100006020010000100001200541200351150201100991004010010000100000100100000110000000100000000000321021071111965840002101001000040100120055120052120036120036120055
50204120102899000000100001200201194931094672560103401001000110000301001006210000107902657363806134461012003012007912006411314931136685010030200100001000060200100001000012005412005111502011009910040100100001000001001000001100000001000010100003210110711119658400021310121000040100120055120055120036120036120055
502041200359000000000100012003911951310944925601034010210000100003010010000100001079035573545561363170120030120097120066113141311365850100302001000010000602001000010000120035120051115020110099100401001000010000010010000011000000010000101000032101251111966140002130121000040100120055120055120055120055120060
502041200518990000001100012003911951310946425601034010210001100003010010000100001079182573916461367300120011120035120054113149311367150100302001000010000602001000010000120051120035115020110099100401001000010000010010000001000000010000101000032101101111196644000210091000040100120055120036120060120036120055

1000 unrolls and 10 iterations

Result (median cycles for code, minus 3 chain cycles): 9.0053

retire uop (01)cycle (02)03l1d tlb fill (05)mmu table walk data (08)09l2 tlb miss data (0b)0e0f18191e1f22243a3f4d4f51schedule 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)6061696d6emap stall dispatch (70)int prf full (71)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 load (98)inst ldst (9b)9fl1d tlb access (a0)l1d tlb miss (a1)l1d cache miss ld (a3)ld unit uop (a6)l1d cache writeback (a8)a9acafb5bbl1d cache miss ld nonspec (bf)l1d tlb miss nonspec (c1)c2cfd0d5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)eaebec? ldst retires (ed)? int retires (ef)f5f6f7f8fd
50025120053899101101002720000120041119499109469256001640014100021000030010100001000010796025736620613376419120057120056120100113216031136805001030020100001000060020100001000012004112005311500211091040010100001000010100022110002011100001101131409910744119671400049681000040010120057120042120057120042120042
5002412004189910000000440000120041119514109466256001340014100021000030010100001000010794635736476613376419120032120056120067113171031136925001030020100001000060020100001000012004112004111500211091040010100001000010100022110002011100000111131409310734119668400049951000040010120042120057120057120042120054
5002412005389911100000740000120041119499109455256001640014100021000030010100001000010794635736476613376419120031120056120053113218031136955001030020100001000060020100001000012005612004111500211091040010100001000010100011110003011100000111131409310734119656400046981000040010120057120042120057120057120042
5002412004189910010000590100120026119499109466256001640014100021000030010100001000010794635736332613376419120029120056120056113171031136955001030020100001000060020100001000012005612004111500211091040010100001000010100012010002021100000101031409410743119668400029981000040010120054120054120057120054120054
500241200538991111000010100120026119514109469256001340014100021000030010100001005510795895735750613321619120032120053120056113171031136955001030020100001000060020100001000012004112005311500211091040010100001000010100032010001111100001111031409610743119671400049981000040010120057120042120042120042120054
500251200418991110000020100120038119556109469256002440012100021000030010100001000010794635736476613376419120032120041120041113171031136805001030020100001000060020100001000012004612004111500211091040010100001000010100031110002014100001111231409410743119671400049001000040010120057120042120057120042120057
5002412004190011100000140101120038119499109469256001640012100021000030010100001000010794635735750613376419120029120056120041113171031136925001030020100001000060020100001000012005612004111500211091040010100001000010100033010003017100001111131409610774119656400040901000040010120042120057120057120042120057
500241200568991000000070100120026119514109455256001640014100011000030010100001000010795755736476613321619120032120056120056113234031136955001030020100001000060020100001000012005312005311500211091040010100001000010100012110002001100001111031409410746119671400040981000040010120057120042120057120057120054
5002412005389910010000620000120038119511109455256001640014100021000030010100001000010796025735750613376419120017120061120053113171031136805001030020100001000060020100001000012005312005311500211091040010100001000010100012010003021100001111131409410744119671400029681000040010120042120057120042120057120057
5002412005689911101100500101120026119499109455256001640012100021000030010100001000010795935736332613376419120032120041120041113171031136925001030020100001000060020100001000012004112005311500211091040010100001000010100012110001001100001111031409310734119668400029981000040010120057120042120054120042120042

Test 3: throughput

Count: 8

Code:

  ldr s0, [x6, #8]
  ldr s0, [x6, #8]
  ldr s0, [x6, #8]
  ldr s0, [x6, #8]
  ldr s0, [x6, #8]
  ldr s0, [x6, #8]
  ldr s0, [x6, #8]
  ldr s0, [x6, #8]
  mov x7, x6
  mov x8, x6
  mov x9, x6
  mov x10, x6
  mov x11, x6
  mov x12, x6
  mov x13, x6

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.3341

retire uop (01)cycle (02)03l1i tlb fill (04)mmu table walk instruction (07)mmu table walk data (08)09l2 tlb miss instruction (0a)l2 tlb miss data (0b)0e0f18191e1f22233a3f4346494f51schedule uop (52)schedule int uop (53)schedule ldst uop (55)dispatch int uop (56)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map ldst uop (7d)map int uop inputs (7f)map ldst uop inputs (80)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 load (98)inst ldst (9b)9d9fl1d tlb access (a0)l1d tlb miss (a1)l1d cache miss ld (a3)a5ld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)a9acafb5b6bbl1d cache miss ld nonspec (bf)c2branch cond mispred nonspec (c5)cfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)eaebec? ldst retires (ed)? int retires (ef)f5f6f7f8fd
802052672820000000000004501012671221212162580100100800001008000050011657890267022672726727166303166858010020080000200800002673126727118020110099100100800008000011008000004308000000038800386139430051102162226733014104800001002673226732267282672826728
80204267272000000000000000002671621120258010010080000100800005001167231126702267272672716650316689801002008000020080000267312672711802011009910010080000800000100800000008003900039800000139440051102162226724010100800001002670826728267282672826732
8020426731200000000000044010026712212121925801001008000010080000500116652512670226727267271665031668580100200800002008000026707267271180201100991001008000080000010080000043080038000080000613900051102162226724010104800001002672826708267082672826728
80204267272000000000100440001267120101925801001008000010080000500116652502670226727267271665031668580100200800002008000026727267271180201100991001008000080000010080000000800390104280000603943005110216222672400104800001002672826728267322672826728
80204267072000000000000450001267142111925801001008000010080000500116723102670626727267311665031666580100200800002008000026731267271180201100991001008000080000010080000043080038000080038613900051102162227135014104800001002672826728267282670826708
802042673120000000011004500012672821120258010010080000100800005001177038126702267272672716654316685801002008000020080000267272672711802011009910010080000800000100800000430800390003980039613944005110216222673200104800001002670826732267322670826728
8020426727200000000000044000126716212016258010010080000100800005001167127026706267312673116654316689801002008000020080000267072672711802011009910010080000800000100800000430800390003980039000430051102162226727014107800001002670826728267082672826708
80204267272000000000100450101267122121162580100100800001008000050011672311267022673126707166543166858010020080000200800002672726727118020110099100100800008000001008000004308000000039800006139430051102162226724010107800001002673226708267282673226708
80204267312000000000000440000267122120162580100100800001008000050011657890266822670726727166503166858010020080000200800002672726727118020110099100100800008000001008000004308003801039800006039430051102162226724010107800001002672826708267282670826732
8020426727200000000110045010126902212102580100100800001008000050011671270267022672726731166543166858010020080000200800002672726727118020110099100100800008000011008000004308000000062980039013943005110216222679801407800001002670826732267322672826728

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.3341

retire uop (01)cycle (02)030e0f1e223a3f4346494f51schedule uop (52)schedule int uop (53)schedule ldst uop (55)dispatch int uop (56)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)60696b6d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map ldst uop (7d)map int uop inputs (7f)map ldst uop inputs (80)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 load (98)inst ldst (9b)9d9fl1d tlb access (a0)l1d cache miss ld (a3)ld unit uop (a6)l1d cache writeback (a8)acafb5b6bbl1d cache miss ld nonspec (bf)cfd5map dispatch bubble (d6)d9daddfetch restart (de)e0eaebec? ldst retires (ed)? int retires (ef)f5f6f7f8fd
80025267272000045102669321212162580010108000010800005011667501267020267082672716659316707800102080000208000026708267271180021109101080000800000108000043800390388003961043502011169079267281410480000102670926728267292672826709
800242672720000000266930120272580010108000010800005011668861267030267082672716672316688800102080000208000026708267271180021109101080000800000108000043800390080039613943502011168010826776010080000102670926709267092672926728
800242672720000450026693201202580010108000010800005011688430267030267272672716652316708800102080000208000026728267281180021109101080000800000108000043800381398003961390502081680710267051010480000102670926728267312670926729
8002426727201000012671620016258001010800001080000501166750026702326727267081667631668880010208000020800002672826727118002110910108000080000010800004380039008003861394350209168071127213100480000102673226729267282672826729
8002426728200004500267122012162580140108000010800005011667501267020267272672716652316708800102080000208000026708267081180021109101080000800000108000008003903980039013943502011168061026728100480000102670926728267292670926729
80024267082000045112671321201625800101080000108000050116675012670302672726727166723167088001020800002080000267272672711800211091010800008000001080000080000039800396139435020101680108267241010480000102672826729267092672826709
800242672719900451026712012016258001010800001080000501166886026683026728267281667231668880010208000020800002672726728118002110910108000080000010800000800390080039613943502010168079267321010480000102672826728267292670926732
800242673120011451126716212016258001010800001080000501166896026702026727267081667231668880010208000020800002672726727118002110910108000080000010800000800380398004061043502071680101026709010080000102672826709267092686426728
800242670820000450126712201216258001010800001080000501166750126683026728267081667231670880010208000020800002672726728118002110910108000080000010800004380000039800000104350207161001092672800480000102670926728267092673226728
8002426729200004511267122121216258001010800001080000501166886126703026727267271665231670880010208000020800002672726727118002110910108000080000010800004380039008003901394350206161008726725140480000102670926709267282670926709