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

DSB (OSHST)

Test 1: uops

Code:

  dsb oshst

(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)03l2 tlb miss data (0b)1e3f51schedule uop (52)schedule ldst uop (55)dispatch ldst uop (58)simd uops in schedulers (5a)696a6d6emap rewind (75)map stall (76)dispatch uop (78)map ldst uop (7d)8283flush restart other nonspec (84)85inst all (8c)inst barrier (9c)st unit uop (a7)l1d cache writeback (a8)cfd5map dispatch bubble (d6)ddfetch restart (de)e0? ldst retires (ed)f5f6f7f8fd
10041703212800170171580110001000100060004913952148591703231689010001000170321703211100110001000073116111683810001703317033170331703317033
10041703212800170171580110001000100060004913952148591703231689010001000170321703211100110001000073116111683810001703317033170331703317033
1004170321280303170171580110001000100060004913952148591703231689010001000170321703211100110001000073116111683810001703317033170331703317033
10041703212800170171580110001000100060004913952148591703231689010001000170321703211100110001000073116111683810001703317033170331703317033
10041703212700170171580110001000100060004913952148591703231689010001000170321703211100110001000073116111683810001703317033170331703317033
10041703212700170171580110001000100060004913952148591703231689010001000170321703211100110001000073116111683810001703317033170331703317033
10041703212800170171580110001000100060004913952148591703231689010001000170321703211100110001000073116111683810001703317033170331703317033
10041703212800170171580110001000100060004913952148591703231689010001000170321703211100110001000073116111683810001703317033170331703317033
10041703212800170171580110001000100060004913952148591703231689010001000170321703211100110001000073116111683810001703317033170331703317033
10041703212800170171580110001000100060004913952148591703231689010001000170321703211100110001000073116111683810001703317033170331703317033

Test 2: throughput

Code:

  dsb oshst

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 17.0032

retire uop (01)cycle (02)03mmu table walk data (08)l2 tlb miss data (0b)18191e1f3a3f414b51schedule 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)60696a6d6emap rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map ldst uop (7d)map int uop inputs (7f)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst barrier (9c)9fl1d tlb access (a0)l1d tlb miss (a1)ld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)a9acc2cfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? int retires (ef)f5f6f7f8fd
1020417003212730000105900170144001597001010010010000100100005005980004916695215094317003231687401010020010000200170032135919111020110099100100100001000001000010307101161116983859999100170033170033170033170033170033
10204170032127400000001700170015970010100100100001001000050059800049166952150935170032316874010100200100002001700321359191110201100991001001000010000010000000071011611169838010000100170033170033170033170033170033
10204170032127300000001700172015970010100100100001001000850059800049166952150935170032316874010100200100002001700321359191110201100991001001000010000010000200071011611169838010000100170033170033170033170033170033
10204170032127400000001700170015970010100100100001001000050059800049166952150993170032316874010100200100002001700321359191110201100991001001000010000010000000071011611169838010000100170033170033170033170033170033
10204170032127400000001700170015970010100100100001001000050059800049166952150935170032316874610100200100002001700321359191110201100991001001000010000010000003071011611169838010000100170033170033170033170033170033
1020417003212740000129000170017001597001010010010000100100005005980004916695215093517003231687401010020010000200170032135919111020110099100100999910000010000000071011611169838010000100170033170033170033170033170033
10204170032127300000001700170015970010100100100001001000050059800049166952150994170032316874010100200100002001700321359191110201100991001001000010000010000000071011611169838010000100170033170033170033170033170077
10204170032127400000001700170015970010100100100001001000050059800049166952150935170032316874010100200100002001700321359191110201100991001001000010000010000100071011611169838010000100170053170033170033170033170033
10204170032127400000001700170015970010100100100001001000050059800049166952150935170032316874010100200100002001700321359191110201100991001001000010000010000000071011911169838010000100170033170033170033170033170033
10204170032127400000001700170015970010100100100001001001650059800049166952150987170032316874010100200100002001700321359191110201100991001001000010000010000000071011611169838010000100170033170033170033170033170033

1000 unrolls and 10 iterations

Result (median cycles for code): 17.0032

retire uop (01)cycle (02)03mmu table walk data (08)l2 tlb miss data (0b)18191e1f3a3f414b51schedule 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)60696a6b6d6emap rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map ldst uop (7d)map int uop inputs (7f)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst barrier (9c)9fl1d tlb access (a0)l1d tlb miss (a1)ld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)a9acc2branch cond mispred nonspec (c5)branch mispred nonspec (cb)cfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? int retires (ef)f5f6f7f8fd
10024171942128901636279564984017001700159786100101010000101000050599801491669520149957170032316876210010201000020170032170032111002110910101000010000100250000006403163316983801000010170033170033170033170033170033
1002417003213180000001170017001597861001010100121010014505998004916695201499571700323168762100102010000201700321700322110021109101010000100001000000000065851202316984321000010170049170033170169170033170033
100241700321273000000017001700159920100101010057121000050599800491669520150084170032316876210010201000020170248170032111002110910101000010400100000000006403163316983801000010170033170033170033170033170033
100241700321297000000017004900159786100101010000101001350599800491669520149981170071616876210010201000820170032170032211002110910101000010000100000000006402163316983801000010170033170033170033170033170033
100241700321306000000017044500159786100101010000121000065605790491669520150031170032316876210020201000020170032170032111002110910101000010000100001060006403163216983801000010170033170033170033170033170033
100241700321273000060017010300159786100101010000101000050599801491669520149957170032616876210010201000020170079170032111002110910101000010000100583021754006583412316983801000010170033170033170033170033170033
100241700321273010000017001700159786100211010000101000050599800491669520149977170032140170073104642010468241719481720104211002110910101000010000100841090007214162216983801000010170033170033170057170033170033
10024170032127300001200170259001597001009410100091110000506197409816695231553861724283168762100102010000201700321701121110021109101099991000010000077430206403164316986841000010170033170062170033170033170033
1002417003212740010400017001720159786100101010012101000060599800491669520150114170032616879410203201007120170066170032111002110910101000010020100000000006403163316983821000010170033170155170229170070170033
10024170032127300000001700170015978610010101000010100005059980049166952014997317007931687931008120102792217211617198957110021109101010000100221003416241149800082543053316983811000010170033170185170033170160170033