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

ST3 (single, B)

Test 1: uops

Code:

  st3 { v0.b, v1.b, v2.b }[1], [x6]
  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

(no loop instructions)

1000 unrolls and 1 iteration

Retires (minus 60 nops): 2.000

Issues: 2.000

Integer unit issues: 0.000

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)18191e1f3a3f4951schedule uop (52)schedule simd uop (54)schedule ldst uop (55)dispatch simd uop (57)dispatch ldst uop (58)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)e0eaebec? ldst retires (ed)? simd retires (ee)f5f6f7f8fd
6200629359236115201800012046432921301846720001000100010001000109058000122174928357285683102000100010002000300028715285681161001100010001000020100000246100003000133461000070193206847200533187381911453828126151611261314211100010002874428598286612866528591
62004287112220220015100024922284940176652000100010001000100010908800052170728481285973102000100010002000300028572287601161001100010001002321100101110001211013460975770173199343199573327381519414128136153341251614069100010002857628617286562864228735
620042868322201900210000047682836301763320001000100010001000109058000621732284812859331020001000100020003000285732861211610011000100010000201000007010001211013207949470373232546201253192381217484628153150591260114125100010002862028706286512872028647
620042880622101400140000047742853301761320001001100010001000109028000112175128453286043102000100010002000300028555286171161001100010001000020100000010000011013276959370033220544200113272382113434528146150551269714262100010002870928627286502860728662
6200428659221118111500001487228620117618200010001000100010001089880001217032838628734310200010001000200030002860828727116100110001000100122110010139110001212013319935070313220944199873220380810434128147156031254813980100010002863028659286782862128614
620042875022201800260001204909285911177652000100010001000100010908800052175228421286293102000100010002000300028653285801161001100010001002302100101110000200013164965569783344743199533176381610424128174155641275614225100010002873828582286442862128601
62004285932220190017000004858284660176272000100010001000100010906800062174328432286953102000100010002000300028573285891161001100010001000000100000010000200013137945670583214749200463249380813344228097151551266513986100010002866528671285962865328610
620042871022011310171000148072846601762320001000100010001000109098000102169728461286973102000100010002000300028543287571161001100010001003120100101110000200013304979970773242643200593222380913384728117148911272614023100010002871128540285572846728631
62004286262230180012000120472328404017551200010001000100010001091080009217262850628677310200010001000200030002871828714116100110001000100113210010211000101001364995826989315964020084328638138464328196153611269213998100010002852428712286692871328667
62004286062230170011000014836285440176202000100010001000100010903800072175328479287533102000100010002000300028603286511161001100010001000020100000010000000013423961270973230546200133191380811454128150148151241314013100010002869428782286092866628684

Test 2: throughput

Count: 8

Code:

  st3 { v0.b, v1.b, v2.b }[1], [x6]
  st3 { v0.b, v1.b, v2.b }[1], [x6]
  st3 { v0.b, v1.b, v2.b }[1], [x6]
  st3 { v0.b, v1.b, v2.b }[1], [x6]
  st3 { v0.b, v1.b, v2.b }[1], [x6]
  st3 { v0.b, v1.b, v2.b }[1], [x6]
  st3 { v0.b, v1.b, v2.b }[1], [x6]
  st3 { v0.b, v1.b, v2.b }[1], [x6]
  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): 0.5007

retire uop (01)cycle (02)03l1d tlb fill (05)mmu table walk data (08)09l2 tlb miss data (0b)18191e1f24373a3f46494f51schedule 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)cdcfd0d5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
160206400703101002001220014611400391616149162476100824478000010080000800005001839976647400040029400504005019961320020160100200800008000020016000024000040052400511180201100991001008000080000100800141544018001401289800001643142000511051161140051080000800001004004940049400524005440055
1602044007031010000012170182714003600725162756100828318000010080000800005001840072643892040027400504005219966320005160100200800008000020016000024000040050400471180201100991001008000080000100800151444018001600303800021644140000511001161240051080000800001004006340051400514006440055
1602044006731010010001502439140036160125163825100823968000010080000800005001840048649505040025400504005419962320012160100200800008000020016000024000040050400541180201100991001008000080000100800141444008001600282800021644141000511001161140047080000800001004004840052400524005240054
1602044006331011110012190121314003501602516217010083187800001008000080000500183990464956204002940063400501997332001216010020080000800002001600002400004005240054118020110099100100800008000010080015154401800141118800021444140000511001161140048080000800001004006340052400634006340055
1602044005331010010001702293140033161602516378510081446800001008000080000500184007264238504002540050400541996732001216010020080000800002001600002400004006240054118020110099100100800008000010080015144401800161015800021444140000511001161140051080000800001004005140063400514005140055
1602044005431010100001502882140036161602516373210083173800001008000080000500184045664797504002240050400511997632000516010020080000800002001600002400004005040051118020110099100100800008000010080014144400800160018800021644140000511001161140048080000800001004005140051400554005540052
160204400503101000000170198914003201602516306210082504800001008000080000500184014464794404002540047400531996732002016010020080000800002001600002400004005240207118020110099100100800008000010080014144402800160117800021644141000511001161140050080000800001004005440055400544005340055
16020440054310100100021026481400360002516368110083359800001008000080000500184002464378504002540050400501996232001216010020080000800002001600002400004006340054118020110099100100800008000010080015144400800161114800021644140000511001162240051080000800001004005540055400514005140054
1602044005231010000001402021140238161614225162657100821078000010080000800005001840168646660040024400494025219965320173160100200800008012020016000024000040054400471180201100991001008000080000100800151500180016001069800021644140000511001161140049080000800001004005540054402594005440052
1602044005231011000001403869140035161614716272810082781800001008000080108500184007265056904002940063402571996711200121601002008000080000200160000240000400624005021802011009910010080000800001008019414442941800160114800621644141000511001161140047080000800001004006340054400514024840055

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5005

retire uop (01)cycle (02)03mmu table walk data (08)l2 tlb miss data (0b)18191e1f222324373a3f46494f51schedule 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)rob full (74)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)91inst 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)acafbcl1d cache miss st nonspec (c0)c2cfd5map dispatch bubble (d6)ddfetch restart (de)e0? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
160026400423100000031004695040027161602516003910800318000010800008000050183971264008440023400434004219982032002316001020800008000020160000240000400424004311800211090101080000800001080000034008000205800022340502051643400408000080000104004440043400444004340049
1600244004231100000910056040028161602516379610819338000010800008000050183971264009440021400434004819988032002216001020800008000020160000240000400434004811800211090101080000800001080000034008000215800022340502031643411278000080000104004340044400434004440044
160024400483170000031004035040029161602516198010828768000010800008000050183971264616440024400424004919982032002216001020800008000020160000240000400434004211800211090101080000800001080000034008000202800022340502031643400408000080000104005040050407254004940044
160024400423110000031003425040034161612516229010808708000010800008000050183983264442840021400424004319982032002316001020800008000020160000240000400424004311800211090101080000800001080000034008000215800022340502031643400398000080000104004440043400444004340043
1600244004931100000610028604002816160251600481081427800001080000800005018398086493104002340043400481998203200221600102080000800002016000024000040043400421180021109010108000080000108000000008000205800022340502031635400458000080000104004440043400444004340043
1600244004931000110310043040033161602516149410800368000010800008000050183971264505240024400424004919982032002316001020800008000020160000240000400424004911800211090101080000800001080000034008000200800022340502041665400468000080000104004340044400434004440044
1600244004331100001231003911040033161602516454910851418000010800008000050183971264011140021400424004219982032002816001020800008000020160000240000400494004211800211090101080000800001080000034208000205800002340502031643400408000080000104004440043400434004340050
1600244004231100000310022040922161602516009610815628000010800008000050183971264009340021400434004819982032002316001020800008000020160000240000400494004311800211090101080000800001080000034008000202800022340502031665400398000080000104005040050400434005040043
1600244004331000001261004113040028161602516452010817718000010800008000050183971265410640021400434004219984032002216001020800008000020160000240000400434004211800211090101080000800001080000034008000202800022340502041636400408000080000104005040050400494004940044
160024400423130000030013105040027161602516157210838748000010800008000050183971264587440024400424004919985032002316001020800008000020160000240000400424004911800211090101080000800001080000034008000202800022340502021644400398000080000104004440043400444004340043