Apple M1 Microarchitecture Research by Dougall Johnson

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

CMGE (zero, 4S)

Test 1: uops

Code:

  cmge v0.4s, v0.4s, #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)03080b1e3f4e51inst 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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715000110168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371600061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371600061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500082168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715000611686251000100010002645211201820372037157131895100010001000203720371110011000001273116111786100020382038203820382038
1004203715001261168625100010001000264521120182037203715713189510001000100020372037111001100001073116111786100020382038203820382038
100420371600061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715002782168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmge v0.4s, v0.4s, #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)031e3f4e51inst 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)9fa9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715012103196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000204100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000607101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101171119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03191e3f4e51inst 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
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640616221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020090200372003718443318767100102010000201000020037200371110021109101010000100662216221978610000102003820038200382003820038
10024200371500486119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150096119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715003276119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000106640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmge v0.4s, v8.4s, #0
  cmge v1.4s, v8.4s, #0
  cmge v2.4s, v8.4s, #0
  cmge v3.4s, v8.4s, #0
  cmge v4.4s, v8.4s, #0
  cmge v5.4s, v8.4s, #0
  cmge v6.4s, v8.4s, #0
  cmge v7.4s, v8.4s, #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)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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181160020035800001002003920039200392003920039
8020420038150351502580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204201131500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001001011151180160020035800001002003920039200392003920039
8020420038150393292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815005762580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898022420080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920099

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e1f3f51inst 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)9fa8acc5cdcficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500003925800101080000108029550640000120019200382003899963100188001020800002080000200382003811800211091010800001003005020081615152009680000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020017161772003580000102003920039200392003920039
800242003815000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000050200171617172003580000102003920039200392003920039
8002420038150000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000101300502007161772003580000102003920039200392003920039
80024200381500003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001003005020071617172003580000102003920039200392003920039
800242003815000039258001010800941080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010100050200141617172003580000102003920039200392003920039
80024200381500003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000005020017161582003580000102003920039200392003920039
80024200381500003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001010005020017167172003580000102003920039200392003920039
8002420038150000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000101000502007161772003580000102003920039200392003920039
800242003815006039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000050200171617172003580000102003920039200392003920039