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 (SY)

Test 1: uops

Code:

  dsb sy

(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)18191e1f3a3f51schedule 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)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? ldst retires (ed)f5f6f7f8fd
1004170321280000001701715801100010001000600004913952148591703231689010001000170321703211100110001000373316111683810001703317033170331703317033
1004170321270009001701715801100010001000600014913952148751703231689010001000170321703211100110001000073116111683810001703317033170331703317033
100417058128111316601701715801100010111011600014913952148621703231689010001000170321703211100110001000073116111683810001703317033170331703317033
1004170321280000001701715801100010001000600014913952148591703231689010001000170321703211100110001000073116111683810001703317033170331703317033
1004170321270000001701715801100010001000600014913952148671703231689010001000170321703211100110001000073116111683810001703317033170331703317033
1004170321270000001701715801100010001000600014913952148591703231689010001000170321703211100110001000073116111683810001703317033170331703317033
1004170321280000001701715801100010001000600014913952148591703231689010001000170321703211100110001000073116111683810001703317033170331703317033
1004170321270000011701715801100010001000600004913952148671703231689010001000170321703211100110001000073116111683810001703317033170331703317033
1004170321280000001701715801100010001000600004913952148611703231689010001000170321703211100110001000073116111683810001703317033170331703317033
1004170321270000001701715801100010001000600014913952148591703231689010001000170321703211100110001000073116111683810001703317033170331703317033

Test 2: throughput

Code:

  dsb sy

(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)18191e1f3a3f51schedule 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)cdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? int retires (ef)f5f6f7f8fd
1020417003212740000000170017159700101001001000010010000500598001491669520150935170032316874010100200100002001700321359191110201100991001001000010000010000000000071011601169838010000100170033170033170033170033170033
10204170032127300002700170017159700101001001000010010000500598001491669520150935170032316874010100200100162001700321359191110201100991001001000010000010000000000071011611169838010000100170033170033170033170033170033
1020417003212740000000170017159700101001001000010010000500598001491669520150935170032316874010100200100002001700321359191110201100991001001000010000010000000000071011611169838010000100170033170033170033170033170033
1020417003212740000000170017159700101001001000010010000500598001491669520150939170032316874010100200100002001700321359191110201100991001001000010000010000000000071011611169838010000100170033170033170033170033170033
10204170032127400001500170017159700101451001000010010000500598001491669520150935170032316874010100200100002001700321359191110201100991001001000010000010000000000071011611169838010000100170033170033170033170033170033
1020417003212740000000170017159700101001001000010010000500598001491669520150997170032316874010100200100002001700321359191110201100991001001000010000010000000000071011611169838010000100170033170033170033170033170033
1020417003212740000000170017159700101001001000010010013500598001491669850151146170236171690841016921010461204171534171437441102011009910010010000100222104221215345200011933369321708322510000100171431171631171450171809171795
102041716941284103347459336340171902160341103751241000010010000500598001491669520150987170032316874010100200100002001700321359191110201100991001001000010000010000000000071011611169838010000100170033170033170033170033170033
1020417003212740000000170017159700101001001000010010000500598000491669520150935170032316874010100200100002001700321359191110201100991001001000010000010000000000071011611169838010000100170033170033170033170033170033
1020417003212730000000170017159700101001001000010010000500598001491669520150935170032316874010100200100002001700321359191110201100991001001000010000010000000000071011611169838010000100170033170033170033170033170033

1000 unrolls and 10 iterations

Result (median cycles for code): 17.0032

retire uop (01)cycle (02)03mmu table walk data (08)18191e1f3f51schedule 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)9fst unit uop (a7)l1d cache writeback (a8)a9acbranch cond mispred nonspec (c5)cdcfd2d5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? int retires (ef)f5f6f7f8fd
10024170032127400000170017159786100101010000101000050599800491669520150033170032316876210010201000020170032170032111002110910101000010100000000064003163316983801000010170033170033170033170033170033
100241700321274000210170017159786100101010000101000050599800491669520149957170032316876210010201000020170032170032111002110910101000010100000000064003163316983801000010170057170033170033170033170033
10024170032127300090170017159786100101010000101000060599800491669520149957170032616876210010201000920170032170032511002110910101000010100000000064002163316983801000010170033170033170033170033170033
10024170032127400000170017159786100101010000101000050599801981669520149957170037316876210010201000020170032170032111002110910101000010100000000064002162216983801000010170033170033170033170033170033
10024170032127400060170017159786100101010000101001950599801491669520150166170037316876210010201000020170032170032111002110910101000010100000000064002163316983801000010170033170033170033170033170033
10024170032127300000170017159786100101010000101000050599801491669520149957170037316876210010201000020170032170032211002110910101000010100000000064002163316983801000010170033170033170033170033170033
10024170032127400060170017159786100101010000101000050599801491669520149957170037316876210010201000020170032170032111002110910101000010100000030064002163316983801000010170033170033170033170033170033
10024170032127400000170017159786100101010000101000050599800491669520150031170037316876210010201000020170032170032111002110910101000010100000000064003163216983801000010170033170033170033170033170033
100241700321274010300170017159786100101010000101000050599800491669520149957170037316876210010201000020170032170032111002110910101000010100191200064002162216983801000010170033170033170033170033170162
10024170032127402018204170017159786100101010000101000050599800491669520149957170037316876210010201000020170032170032111002110910101000010100000030064003163316983801000010170033170033170033170033170116