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 (ST)

Test 1: uops

Code:

  dsb st

(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)03191e1f3f51schedule uop (52)schedule ldst uop (55)dispatch ldst uop (58)simd uops in schedulers (5a)60696a6d6emap 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)cfd5map dispatch bubble (d6)ddfetch restart (de)e0eb? ldst retires (ed)f5f6f7f8fd
10041703212702401701715801100010001000600014913957148631703231689010001000170321703211100110001000731161116838010001703317033170331703317033
1004170321270001701715801100010001000600004913957148591703231689010001000170321703211100110001000731161116838110001703317033170331703317033
10041703212803001701715801100010001000600004913957148591703231689010001000170321703211100110001000731161116838010001703317033170331703317033
1004170321270001701715801100010001000600014913957148591703231689010001000170321703211100110001000731161116838010001703317033170331703317033
100417032127027001701715801100010001000600004913957148591703231689010001000170321703211100110001000731161116838010001703317033170331703317033
1004170321280001701715801100010001000600014913957148591703231689010001000170321703211100110001000731161116838010001703317033170331703317033
1004170321280001701715801100010001000600004913957148591703231689010001000170321703211100110001000731161116838010001703317033170331703317033
100417032127026401701715801100010001000600004913957148631703231689010001000170321703211100110001000731161116838010001703317033170331703317033
1004170321270001701715801100010001000600014913957148591703231689010001000170321703211100110001000731161116838010001703317033170331703317033
10041703212805101701715801100010001000600004913957148661703231689010001000170321703211100110001000731161116838010001703317033170331703317033

Test 2: throughput

Code:

  dsb st

(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)18191e1f3a3f4b51schedule 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)a9acc2cdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? int retires (ef)f5f6f7f8fd
102041700321273000000017001701597001010010010000111100005005980004916695715103617007315168910101532001000020017003213591911102011009910010010000100000100000000071011611169838010000100170033170033170033170033170033
102041700321274000032736401700170159700101001001000010010000500598000491669571509351700323168740101002001000020017003213591911102011009910010010000100000100000000080611611169838110000100170033170033170033170033170033
10204170032127400000001700170159700101001001000010010000500598000491669571509351700323168740101002001000020017003213591911102011009910010010000100000100000000071011621169838010000100170033170033170033170033170033
10204170032127400000001700170159700101001001000010010000500598000491669571509351700323168740101002001000020017003213591911102011009910010010000100000100000000071011611169838010000100170033170033170033170033170033
10204170032127400000001700170159700101001001000010010000500598000491669571509351700323168740101002001000020017003213591911102011009910010010000100000100000000071011611169838010000100170049170033170033170033170033
10204170032127400000001700170159700101001001000010010000500598000491669571509351700323168740101002001000020017003213591911102011009910010010000100000100000000071011611169838010000100170033170033170033170033170033
102041700321273000021001700170159700101001001000010010000500598000491669571509351700323168740101002001000020017003213591911102011009910010010000100000100000000071011611169838010000100170033170033170033170033170033
10204170032127300000001700170159700101001001000010010000500598000491669571509961700323168740101002001000020017003213591911102011009910010010000100000100000000071011611169838010000100170033170033170033170033170033
10204170032127400000001700170159700101001001000010010000500598000491669571509351700323168740101002001001520017003213591911102011009910010010000100000100000030071011611169838010000100170033170033170033170033170033
10204170032127300000001700171159700101001001000010010000500598000491669571509351700323168740101002001000020017003213591911102011009910010010000100000100000000071011611169838010000100170033170033170033170033170033

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)18191e3f4b51schedule 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)9fst unit uop (a7)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? ldst retires (ed)? int retires (ef)f5f6f7f8fd
100241700321274000001700170159786100101010000101000050599800491669521499571700323168762100312010000201700321700321110021109101010000101000000640416221698381000010170033170033170033170033170033
100241700321274000001700170159786100101010000101000050599800491669521500381700329168762100102010000201700321700321110021109101010000101000000640216221698381000010170033170033170033170033170033
100241700321274000001700170159786100101010000101000050599800491669521499571700323168762100102010000201700321700322110021109101010000101000000640216221698381000010170033170033170033170033170033
100241700321273000001700170159786100101010000101000050599800491669521499571700323168762100102010000201700321700321110021109101010000101000000640316331698381000010170033170033170033170033170033
100241700321274000001700170159786100101010000101000050600450491669521500371700323168762100102010000201700321700321110021109101010000101000000640216221698381000010170033170033170033170033170033
100241700321273000001700170159786100101010000101000050599801491639001499571700323168762100102010000201700321700321110021109101010000101000000640316331698381000010170033170033170033170033170033
100241700321274000091700170159786100101010000101000050599801491669521499571700323168762100102010000201700321700321110021109101010000101000000640216331698381000010170033170033170033170033170033
100241700321274000001700170159786100101010000101000050599800491669521500281700323168762100102010000201700321700321110021109101010000101000010640316331698381000010170033170033170033170033170033
100241700321274000001700170159786100101010000101000050599801491669521499571700323168762100102010000201700321700321110021109101010000101000000640216221698381000010170033170033170033170033170033
100241700321274000001700170159786100101010000101000050599801491669521499571700323168762100102010000201700321700321110021109101010000101000010640316231698381000010170033170033170033170033170033