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 (LD)

Test 1: uops

Code:

  dsb ld

(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)031e3f4b51schedule 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)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? ldst retires (ed)f5f6f7f8fd
1004170321280170170158011000100010006000049139521485917032316890100010001703217032111001100010000073116111683810001703317033170331703317033
1004170321270170170158011000100010006000049139521485917032316890100010001703217032111001100010000073116111683810001703317033170331703317033
1004170321270170170158011000100010006000049139521498117032316890100010001703217032111001100010000073116111683810001703317033170331703317033
1004170321270170170158011000100010006000049139521485917032316890100010001703217032111001100010000073116111683810001703317033170331703317033
1004170321280170170158011000100010006000049139521485917032316890100010001703217032111001100010001073116111683810001703317033170331703317033
10041703212701701701580110001000100060000491395214859170323168901000100017032170321110011000100002773116111683810001703317033170331703317033
1004170321280170170158011000100010006000049139521485917032316890100010001703217032111001100010000073116111683810001703317033170331703317033
1004170321280170170158011000100010006000049139521485917032316890100010001703217032111001100010001073116111683810001703317033170331703317033
1004170321270170170158011000100010006000049139521485917032316890100010001703217032111001100010000073116111683810001703317033170331703317033
1004170321270170170158011000100010006000049139521485917032316890100010001703217032111001100010000073116111683810001703317033170331703317033

Test 2: throughput

Code:

  dsb ld

(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)18191e1f3a3f4151schedule 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)cdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? int retires (ef)f5f6f7f8fd
1020417007313180000000170017015970010100100100001001000050059800149166952015093517003231687401010020010000200170032135919111020110099100100100001000001000000000071011611169838010000100170033170033170033170033170033
10204170032127300000001700170159700101001001000010010000500598000491669520150935170032316874010100200100002001700321359191110201100991001001000010000010000000000710116111698381310000100170033170033170033170033170033
1020417003212730000000170017015970010100100100001001000050059800049166952015106517003231687401010020010000200170032135919111020110099100100100001000001000000000071011611169838010000100170033170053170033170033170033
1020417003212740000000170017015970010100100100001001000050059800149166952015093517003231687401010020010000200170032135919111020110099100100100001000001000000000071011611169838010000100170033170033170033170033170033
1020417003212740000000170017015970010100100100001001000050059800149166952015093517003231687401010020010016200170032135919111020110099100100100001000001000010000071011611169838010000100170033170033170033170033170033
1020417003212730000000170017015970010100100100001001000050059800149166952015167917003231687401010020010000200170032135919111020110099100100100001000001000000000071011611169838010000100170033170033170033170033170033
1020417003212740000000170017015962110100100100001001000050059800149166952015093517003231687401010020010000200170032135919111020110099100100100001000001000020000071011611169838010000100170033170033170033170033170033
1020417003212740000000170017015970010100100100001001000050059800149166952015093517003231687401010020010000200170032135919111020110099100100100001000001000000000071011611169838010000100170033170033170033170033170033
102041700321273000000017001701597001010010010000100100005005980014916695201509951700323168740101002001000020017003213591911102011009910010099991000001000000000071011611169838010000100170033170033170050170033170033
1020417003212740000000170036015971010100100100001001000050059800149166952015093517003231687401010020010000200170032135919111020110099100100100001000001000000000071011611169838010000100170033170033170033170033170033

1000 unrolls and 10 iterations

Result (median cycles for code): 17.0032

retire uop (01)cycle (02)03l2 tlb miss data (0b)181e1f3f51schedule 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)696a6d6emap 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)ld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)acc2cfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? int retires (ef)f5f6f7f8fd
1002417003212740090170017159786100101010000101000050599804916695214995717003231687621001020100002017003217003211100211091010100001000100000306407163316983801000010170033170033170033170033170033
1002417003212730000170017159786100101010000101000050599804916695214995717003231687621001020100002017003217003211100211091010100001020100000306402162316996521000010170116170033170033170033170033
1002417003212740048332170017159786100101010000101000050604564916695215003717015831687621001020100002017003217003211100211091010100001000100000046403162516983801000010170033170033170033170033170033
1002417003212740000170017159786100101210000101003950599804916695214995717003231687621001020100002017003217003211100211091010100001000100000006403162316983801000010170033170033170033170185170033
1002417003212740000170017159854100101010000101000055599804916695214995717003231687621001020100002017003217003211100211091010100001000100000148506402163216983821000010170033170068170033170033170033
1002417003212730000170017159786100171010000101000050599804916695214997317003231687891001020100002017003217003211100211091010100001000100000006403162316983801000010170033170033170033170033170033
1002417003212740000170017159786100101010000101000050599804916695214995717003231687621001020100002017003217003211100211091010100001000100000006403162216996401000010170070170033170033170033170033
1002417003212740060170017159786100101010000101000050599804916695215004317003231687621001020100002017003217003211100211091010100001000100000006402163316983801000010170033170033170033170033170033
1002417003212730000170017159786100101010000101000050599804916695214995717003231687621001020100132017003217003211100211091010100001000100000006403163316983801000010170033170033170033170033170033
1002417003212730000170017159786100101110000101000050599804916695214995717003231687621001020100002017003217003211100211091010100001000100000006402163316983801000010170033170033170033170033170033