Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMLE (vector, zero, 8H)

Test 1: uops

Code:

  fcmle v0.8h, v0.8h, #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)03083f4e51inst 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
100420371507316862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371606116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110003073116111786100020382038203820382038
1004203716033316862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371508216862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmle v0.8h, v0.8h, #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)03091e3f4e51inst 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)9faccdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500010319686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100017101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718431318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500012419686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500014919686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03081e3f4e51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
10024200371500078419686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmle v0.8h, v8.8h, #0
  fcmle v1.8h, v8.8h, #0
  fcmle v2.8h, v8.8h, #0
  fcmle v3.8h, v8.8h, #0
  fcmle v4.8h, v8.8h, #0
  fcmle v5.8h, v8.8h, #0
  fcmle v6.8h, v8.8h, #0
  fcmle v7.8h, v8.8h, #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)03091e1f3f51inst 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)9fa1a6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150000732580108100800081008002050064013212001920038200389977699898012020080032200800322003820038518020110099100100800001000000011151180160020035800001002003920039200392003920039
80204200381500901132580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000010011151180160020035800001002003920039200392003920039
802042003815000029258010810080008100804155006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001478011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202009720038200389977699898012020080032200800322003820038118020110099100100800001000000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000330011151350160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151180160020035800001002003920039200392003920039
80204200381500001572580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151180160020035800001002003920039200392003920039
80204200381500005212580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151180160020035800001002003920039201922003920039
80204200381500390292580108100800081008031350064013202001920038200389977699898041320080032200800322003820038118020110099100100800001000000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e1f3f51inst 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)9fa0acc2cficache miss (d3)d5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150000812580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010094705044026160772003580000102003920039200392003920039
8002420038150000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000503707160862003580000102003920039200392003920039
8002420038150000392580010108000010800005064000011200192003820038999631001880010208000020800002003820038118002110910108000010000503705160892003580000102003920039200392003920039
8002420038150090392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000503707160772003580000102003920039200392003920039
80024200381500005142580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000503805160862003580000102003920039200392003920039
8002420038150000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000503706160582003580000102003920039200392003920039
8002420038150000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000503715160882003580000102003920039200392003920039
8002420038150000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000503708260772007580000102003920039200392003920039
8002420038150000392580010108000010800995064000000200192003820038999631001880010208000020800002003820038118002110910108000010000504007160772003580000102003920039200392003920039
80024200381500003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100005037071601092003580000102003920039200392003920039