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

ZIP1 (vector, 2D)

Test 1: uops

Code:

  zip1 v0.2d, v0.2d, v1.2d
  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire uop (01)cycle (02)03l2 tlb miss data (0b)181e3f4e51schedule uop (52)schedule simd uop (54)dispatch simd uop (57)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map simd uop (7e)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst simd alu (9a)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)f5f6f7f8fd
1004203716000611687251000100010002646800201820372037157231895100010002000203720371110011000073216111787100020382038203820382038
1004203715000611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715000611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203716000611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203716000611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203717000611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715000611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037160012611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203716000611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150002511687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  zip1 v0.2d, v0.2d, v1.2d
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire uop (01)cycle (02)03mmu table walk instruction (07)1e3f4e51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d cache writeback (a8)acbranch cond mispred nonspec (c5)cfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)ea? simd retires (ee)? int retires (ef)f5f6f7f8fd
1020420037155006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
1020420037155006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
1020420037155006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100300710116111979100100001002003820038200382003820038
1020420037156006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000710116111979100100001002003820038202312003820038
1020420037155006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
1020420037156006119687251010010010000100100005002847680120018200372003718422318745101252001000020020000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
1020420037155006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
1020420037155006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
1020420037155006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000710116111979100100001002003820038200382008520038
10204200371551010319687251010010010000100100005002847680120018200372003718422318745101252001000020020000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire uop (01)cycle (02)03l1i tlb fill (04)191e3f4e51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d tlb miss (a1)ld unit uop (a6)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640316331978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640316331978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000102640316331978510000102003820038200382003820038
10024200371510006119687251001010100001010000502847680020018200372008418451318767100102010000202000020037200371110021109101010000100010640316331978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100003640316331978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000099640316331978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100020640316331978510000102003820038200382003820038
1002520037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000117640316331978510000102003820038200382003820122
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640316331978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000319640316231978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  zip1 v0.2d, v1.2d, v0.2d
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire uop (01)cycle (02)03mmu table walk data (08)09l2 tlb miss data (0b)191e3f4e51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d tlb access (a0)ld unit uop (a6)l1d cache writeback (a8)aaacbranch cond mispred nonspec (c5)cfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
1020420037156000003565196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715601000285196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371550000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371560000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371550000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371610000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371550000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371550000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037155000027061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371550000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire uop (01)cycle (02)03l2 tlb miss data (0b)1e3f4e51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d cache writeback (a8)acbranch mispred nonspec (cb)cfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
1002420037155006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000101306402162219785010000102003820038200382003820038
1002420037156006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037155006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037156006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000102006402162219785010000102003820038200382003820038
1002420037156006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382008520038
1002420037155006119687251001010100001010000502847680020018200372003718444318767100102010169202000020086200371110021109101010000101006402162219785010000102003820038200382003820038
1002420037155006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371560010319687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037155006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037155006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382013220038

Test 4: throughput

Count: 8

Code:

  zip1 v0.2d, v8.2d, v9.2d
  zip1 v1.2d, v8.2d, v9.2d
  zip1 v2.2d, v8.2d, v9.2d
  zip1 v3.2d, v8.2d, v9.2d
  zip1 v4.2d, v8.2d, v9.2d
  zip1 v5.2d, v8.2d, v9.2d
  zip1 v6.2d, v8.2d, v9.2d
  zip1 v7.2d, v8.2d, v9.2d
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2505

retire uop (01)cycle (02)03mmu table walk data (08)l2 tlb miss data (0b)18191e1f3f51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)simd prf full (72)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)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)? simd retires (ee)? int retires (ef)f5f6f7f8fd
802042005815500001504025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000000005110216112003500800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100000000005110116112003500800001002003920039200392003920039
802042003815600000028325801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000000305110116112003500800001002003920039200392003920039
8020420038156000025504025801001008009410080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000000005110116112003500800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000000005110116112003500800001002003920039200392003920039
80204200381560000004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000000005110116112003500800001002003920039200392003920039
802042003816100000031625801001008000010080000500640000112831200382003899730399968010020080000200160000200382003811802011009910010080000100000010005110116112003500800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100000000005110116112003500800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100000000005110116112003500800001002003920039200392003920039
80204200381560000004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000000005110116112003500800001002003920039200392003920039

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire uop (01)cycle (02)03mmu table walk instruction (07)mmu table walk data (08)1e3f51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696b6d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
8002420048155002410425800101080000108000050640000120019020038200389996310018800102080000201600002003820038118002110910108000010005020716672003580000102003920039200392003920039
800242003815500393925800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005020816652003580000102003920039200392003920039
800242003815000663925800101080000108000050640000120019020038200389996310018800102080000201600002003820038118002110910108000010005020516562003580000102003920039200392003920039
800242003815000039258001010800001080000506400001200190200382003899963100188001020800002016000020038200381180021109101080000101605020516462003580000102003920039200392003920039
800242003815000333925800101080000108000050640000120019020038200389996310018800102080000201600002003820038118002110910108000010005020616882003580000102003920039200392003920039
8002420038150002750625800101080000108000050640000120019020038200389996310018800102080000201600002003820038118002110910108000010105056616682003580000102003920039200392003920039
800242003815000243925800101080000108000050640000120019020038200389996310018800102080000201600002003820038118002110910108000010005020616652003580000102003920039200392003920039
800242003815001213925800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005020616652003580000102003920039200392003920039
800242003815000123925800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005020616562003580000102003920039200392003920039
8002420038150003423925800101080000108000050640000120019020038200389996310018800102080000201600002003820038118002110910108000010005020516652003580000102003920039200392003920039