Apple M1 Microarchitecture Research by Dougall Johnson

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

DUP (element, scalar, S)

Test 1: uops

Code:

  dup s0, v0.s[1]
  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
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371606116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  dup s0, v0.s[1]
  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)03181e1f3f4e51inst 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)9fa6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000611968625101001001000010010000500284752102001820037200371842861874110100200100082001000820037200371110201100991001001000010001011171701600198000100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752112001820037200371842861874110100200100082001000820037200371110201100991001001000010000011171801600198000100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010001794300071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010001300071011611197910100001002003820038200382003820038
10204200371500001031968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010002300071011611197910100001002003820038200382003820038
10204200371500120611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010002300071021611197910100001002003820038200382003820038
10204200371501144881241967525101001211001210010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010001900071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010001000071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000600071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010001600071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)033f4e51inst 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)60696b6d6edispatch 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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150611968625100101010000101000050284752102001802003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038
1002420037150611968625100101010000101000050284752102001802003720037184431018767100102010000201000020037200371110021109101010000100000114640216221978610000102003820038200382003820038
1002420037150611968625100101010000101000050284752102001802003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038
1002420037150611968625100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000100640216221978610000102003820038200382003820038
1002420037150611968625100101010000101000050284752102001802003720037184433187671001020100002010000200372003711100211091010100001000100640216221978610000102003820038200382003820038
10024200371509419686251001010100001010000502847521120018020037200371844331876710160201000020100002003720037111002110910101000010000018640216221978610000102003820038200382003820038
1002420037150611968625100101010000101000050284752102001802003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038
1002420037150611968625100101010000101000050284752102001802003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038
1002420037150611968625100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000300640216221978610000102003820038200382003820038
1002420037150611968625100101010000101000050284752102001802003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  dup s0, v8.s[1]
  dup s1, v8.s[1]
  dup s2, v8.s[1]
  dup s3, v8.s[1]
  dup s4, v8.s[1]
  dup s5, v8.s[1]
  dup s6, v8.s[1]
  dup s7, v8.s[1]
  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)03191e3f51inst 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)9fa0a1a6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181160020035800001002003920039200392003920039
8020420038150006427801161008001610080028500640196020028200492004999769998680128200800382008003820049200491180201100991001008000010000005422251281231120046800001002005020049200492005020049
802042004915000642680116100800161008002850064019612002820048200489976999868012820080038200800382004820048118020110099100100800001000000022251291231120046800001002004920049200492004920049
8020420048150009462780116100800161008002850064019612002820049200489976999868012820080038200800382004820049118020110099100100800001000000022251282231120045800001002004920050200492004920049
8020420048150006426801161008001610080028500640196020028200492004999761099868012820080038200800382004820048118020110099100100800001000000022251281231120046800001002005020050200492004920049
80204200491500064268011610080016100800285006401960200282004820049997610998680128200800382008003820049200481180201100991001008000010000017822251291231120045800001002004920050200502005020049
8020420049150007292680116100800161008002850064019602002820048200489976999868012820080038200800382004920049118020110099100100800001000000022251281231120045800001002005020050200492004920050
802042004815000642780116100800161008002850064019612002820048200489976999868012820080038200800382004820048118020110099100100800001000000022251281231120045800001002004920050200492004920050
802042004815000642780116100800161008002850064019612002820048200489976999868012820080038200800382004920048118020110099100100800001000000022251281231120045800001002004920049200492004920049
8020420049150006426801161008001610080028500640196120028200492004899761099868012820080038200800382004820048118020110099100100800001000000022251291231120045800001002004920049200492004920050

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e1f3a3f51inst 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)9fa1a8accfd0d2icache miss (d3)d5d6ddinst fetch restart (de)dfe0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150000019972580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100205024300816783200350080000102003920039200392003920039
80024200381500000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100005024300616653200350080000102003920039200392003920039
800242003816000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001003095024300516653200350080000102003920039200392003920039
800242003815000001252580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100005024300616783200350080000102003920039200392003920039
80024200381500000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100005024300516563200350080000102003920039200392003920039
800242003815000005522580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100005024300516563200350080000102003920039200392003920039
80024200381500000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100005024300516563200350080000102003920039200392003920039
80024200381500000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100005024300516783200350080000102003920039200392003920039
8002420038150000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010140875024300516563200350080000102003920039200392003920039
800242003815000003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050243001016653200350080000102003920039200392003920039