Apple M1 Microarchitecture Research by Dougall Johnson

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

CMLE (zero, 16B)

Test 1: uops

Code:

  cmle v0.16b, v0.16b, #0
  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
100420371606116862510001000100026452112018203720371571318951000100010002037203711100110002073116111786100020382038203820382038
100420371606116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037151326116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037208411100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371606116862510001000100026452112018203720371571318951000100010002037203711100110000373116111786100020382038203820382038
100420371508216862510001000100026452112018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
1004203715156116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmle v0.16b, v0.16b, #0
  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)03080918193f4e51inst 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)9fa8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010030307101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010010007101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010020007101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000907101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100003007101161119791100001002003820038200382003820038
10204200371490000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308181e3a3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000022521968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100364410165101978610000102003820038200382003820038
10024200371490062621968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000101664411165101978610000102003820038200382003820038
10024200371500002621968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000101964481611111978610000102003820038200382003820038
10024200371500002621967545100221010012101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100144644101610101978610000102003820038200382003820038
100242003715000026219686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001023644131610101978610000102003820038200382003820038
100242003715000026219686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001016644101610101978610000102003820038200382003820038
10024200371500002621968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000102964451610101978610000102003820038200382003820038
10024200371500002621968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000104964411161051978610000102003820038200382003820038
100242003715000026219686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001016064410165111978610000102003820038200382003820038
100242003715000026219686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001029644101611111978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmle v0.16b, v8.16b, #0
  cmle v1.16b, v8.16b, #0
  cmle v2.16b, v8.16b, #0
  cmle v3.16b, v8.16b, #0
  cmle v4.16b, v8.16b, #0
  cmle v5.16b, v8.16b, #0
  cmle v6.16b, v8.16b, #0
  cmle v7.16b, v8.16b, #0
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)031e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420047150034258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000911151181160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010019011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001001011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001003011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001001011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b18191e1f3f51inst 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)6061696d6edispatch 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)9fa0a1a6a7a8a9acc2cfd0d2d5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000000001442580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020002160662003580000102003920039200392003920039
80024200381500000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020002162532003580000102003920039200392003920039
80024200381500000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020003164652003580000102003920039200392003920039
800242003815000000001022580010108000010800005064000000200192003820098999631001880010208000020800002003820038118002110910108000010000000005020005162322003580000102003920039200392003920039
80024200381500000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020006160352003580000102003920039200392003920039
80024200381500000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020003160232003580000102003920039200392003920039
800242003815000000001232580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020003162532003580000102003920039200392003920039
80024200381500000000392580010108000010800005064000015200192003820038999631001880010208000020800002003820038118002110910108000010000000005020005162532003580000102003920039200392003920039
800242003815000000001442580010108000010800005064000015200192003820038999631001880109208000020800002003820038118002110910108000010000000005020542160362003580000102003920039200392003920039
800242003815000000002132580010108000010800005064000015200192003820038999631001880010208000020800002003820038118002110910108000010000000005020006160832003580000102003920039200392003920039