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: 0.001

Load/store unit issues: 1.000

SIMD/FP unit issues: 0.000

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule ldst uop (55)dispatch ldst uop (58)simd uops in schedulers (5a)dispatch uop (78)map ldst uop (7d)? int output thing (e9)? ldst retires (ed)
100416033100111000100040001000100011000
100416033100111000100040001000100011000
100416028100111000100040001000100011000
100416028100111000100040001000100011000
100416028100111000100040001000100011000
100416028100111000100040001000100011000
100416028100111000100040001000100011000
100416028100111000100040001000100011000
100416028100111000100040001000100011000
100416028100111000100040001000100011000

Test 2: throughput

Code:

  dsb sy

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 16.0028

retire uop (01)cycle (02)schedule 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)dispatch uop (78)map int uop (7c)map ldst uop (7d)map int uop inputs (7f)? int output thing (e9)? ldst retires (ed)? int retires (ef)
10204160033101051011000410010039300443881013920010039200110000100
10204160033101051011000410010004300400161010420010004204110000100
10204160509102201021011810110113303431021021420210113204110000100
10204160454102281041012410310040300441181014020010040200110000100
10204160063101141011001310010004300400161010420010004200110000100
10204160441101691011006810010050306409761015220410050200110000100
10204160028101071011000610010004300400161010420010004200110000100
10204160057101131011001210010148309435921025120610148200110000100
1020416058610252102101501011017330042500102732011017320219999100
10204160028101051011000410010004300400161010420010004200110000100

1000 unrolls and 10 iterations

Result (median cycles for code): 16.0028

retire uop (01)cycle (02)schedule 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)dispatch uop (78)map int uop (7c)map ldst uop (7d)map int uop inputs (7f)map ldst uop inputs (80)? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)
1002416003310017111000610100063040024100162010006200110000010
1002416003310011111000010100003040000100102010000200110000010
1002416002810011111000010100113040044100212010011200110000010
1002416002810011111000010100003040000100102010000200110000010
1002416002810011111000010100003040000100102010000200110000010
1002416002810011111000010100003040000100102010000200110000010
1002416002810011111000010100043040016100142010004200110000010
1002416002810011111000010100003040000100102010000200110000010
1002416002810011111000010100003040000100102010000200110000010
1002416002810011111000010100163040064100262010016200110000010