Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

AESMC

Test 1: uops

Code:

  aesmc v0.16b, v0.16b
  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 (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715546116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715696116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716816116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371596116862510001000100026452102018203720371571318951000100010002037203711100110000973116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  aesmc v0.16b, v0.16b
  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 (01)cycle (02)0308090b181e1f3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371550000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071021622198240100001002003820137200382003820038
10204200371550000000831968625101001001000010010000500284752120054200372003718421318745101002001000020010000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
1020420037155000000021271968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
10204200371550000000611968625101001001000010010000500284752120018200372003718421318745101002041000020010000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
1020420037155000000090419686251010010010012100101505002847521200182003720037184213187451042220010000200100002003720037111020110099100100100001000000120071021622197910100001002003820038201322003820038
102042003715600009003531968625101001001000010010000500284752120018200372003718421318745101002001000020410000200372003711102011009910010010000100000000071021622198260100001002003820038200382003820085
10204200371550000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
102042003715500000001721968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
102042003715600000001051968625101001001000010010000500284752120018200372003718421318780101002001000021210000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
102042003715600000001051968625101001001000010010000500285004920018200372003718421318745101002001000020010000200372003711102011009910010010000100000630071021623197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080b18191e1f3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037155000000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037155000000008419686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037155000000006119686251001010100001010304502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402165219822010000102003820038200382003820038
1002420084155000000006119686251001010100001010000502847521120018200372003718443318767100102010000201017020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037155000000008419686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
10024200371550000000010519686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219822010000102003820038200382003820038
1002420037155000000006119686251001010100001010152502847521120018200372003718443318767100102010000201016320037200371110021109101010000100000006402162219786010000102003820038200382003820038
100242003715600000000108419686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
10024200371550000000014919686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382008420038
10024200371550010000010519686251001010100001010000502847521120018200372003718443318767103162010000201000020037200371110021109101010000100000006402162219786010000102003820085200382003820038

Test 3: throughput

Count: 8

Code:

  aesmc v0.16b, v8.16b
  aesmc v1.16b, v8.16b
  aesmc v2.16b, v8.16b
  aesmc v3.16b, v8.16b
  aesmc v4.16b, v8.16b
  aesmc v5.16b, v8.16b
  aesmc v6.16b, v8.16b
  aesmc v7.16b, v8.16b
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)0307080a0b18191e1f3a3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a6a7a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581550000000005025801081008000810080020500641708120028200482004899761099868012820080038200800382004920048118020110099100100800001000000011222512822312200450800001002004920049200492005020050
802042004915600000000064268011610080016100800285006401961200282004920048997699986801282008003820080038200482004811802011009910010080000100000000222512824432200450800001002004920049200492009720049
80204200481550000000006427801161008001610080124500640196120028200482004899769998680128200800382008003820048200481180201100991001008000010000005150222512922332200450800001002004920049200492005020049
8020420048155000000000120278011610080016100800285006401961200282004820048997699986801282008003820080038200482004911802011009910010080000100000000222512832313200450800001002015420050200502004920049
802042004915500000000064278011610080111100801275006401960200282004820048997699986801282008003820080038200482004911802011009910010080000100000000222512932313200460800001002004920049200492004920049
8020420048156000000000642780116100800161008002850064019612002820049200489976109986801282008003820080038200492004911802011009910010080000100000000222512832312200450800001002005020049200492004920050
802042004815500000000064278011610080016100800285006401960200282004820048997699986801282008003820080038200482004911802011009910010080000100000000222512832312200450800001002015020050200502005020049
802042004915500000000064278011610080016100800285006401961200282004920048997699986801282008003820080038200482004811802011009910010080000100000000222512832323200460800001002005020049200492004920049
8020420048155000000000642680116100800161008002850064019612002820048200489976109986801282008003820080038200482004811802011009910010080000100000000222512832312200450800001002010420049200492005020049
802042004815610000000064268011610080016100800285006401960200282004820049997610998680128200800382008003820048200481180201100991001008000010000104650222512822313200450800001002004920113201132004920050

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080b18191e1f3a3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a7a8a9acc2cfd5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050155000001658806225800101080000108000050640000002001920038200389996310018801062080000208000020038200381180021109101080000100000004657502012162752003580000102003920039200392009920039
8002420038155000000003925800101080000108000050640000002001920100200389996310018800102080000208000020038200381180021109101080000100020000050205162752003580000102003920039200392003920039
8002420038155000000003925800101080000108000050640000002001920038200389996310018800102080000208000020237200381180021109101080000100000000050204160642003580000102003920039200392003920039
8002420038156000300003925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100400000050204160662003580000102003920039200392003920039
8002420038155000000008125800101080000108000050640000002001920038200389996310018800102080000208000020038200383180021109101080000100000000050205160662003580000102008720039200392003920039
800242003815500000000373258001010800001080000506400000020019200382003810012310018800102080000208000020038200381180021109101080000100000000050207160672003580000102003920039202442003920039
8002420038156000001200392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000468050205160572003580000102003920039200392003920039
8002420038155000000003925800101080094108000050640760002001920038200389996310018800102080000208000020038200381180021109101080000100000023050206162772003580000102003920039200392003920039
8002420186155000000003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050204160562003580000102003920039200392003920039
8002420038156000001213206225800101080000108000050640000002001920038200389996310018800102080000208000020038200384180021109101080000100020100050207160782003580000102003920101200392003920039