Apple M1 Microarchitecture Research by Dougall Johnson

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

CMEQ (zero, 8B)

Test 1: uops

Code:

  cmeq v0.8b, v0.8b, #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)030b1e3f4e51inst 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
1004203715006116862510001000100026452102018203720741571318951000100010002037203711100110000073116111786100020382038203820382038
100420371601815616862510001000100026452102018203720371571318951000100010002037203711100110000973116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110004073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmeq v0.8b, v0.8b, #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)9fa1a6a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150061196862510100100100001001000059628475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000010007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421221874510100200100002001000020037200371110201100991001001000010000101807101161119791100001002003820038200382023020038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000210007101161119791100001002003820038200382003820038
10204200371503061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001002000607101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000450907101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000002007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000040007101161119791100001002003820038200382003820038
10204200371490611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000270307101161119791100001002003820038200382003820038
1020420037149061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038

1000 unrolls and 10 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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715008219686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmeq v0.8b, v8.8b, #0
  cmeq v1.8b, v8.8b, #0
  cmeq v2.8b, v8.8b, #0
  cmeq v3.8b, v8.8b, #0
  cmeq v4.8b, v8.8b, #0
  cmeq v5.8b, v8.8b, #0
  cmeq v6.8b, v8.8b, #0
  cmeq v7.8b, v8.8b, #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)03090a0b1e3f51inst 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)9fa0a6a8acc5branch mispredict (cb)cdcfd6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571502000712580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
802042003815000001132580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
802042003815000004952580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
8020420038150000015332580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
802042003815000003432580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
802042003815000006012580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
802042003815000002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000383111511816020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)9fa8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000502050716472003580000102003920039200392003920039
80024200381500039258001010800001080000506400000520019200382003899963100188001020800002080000200382003811800211091010800001000502050616342003580000102003920039200392003920039
80024200381500039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000502000516442003580000102003920039200392003920039
80024200381500039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000502000416342003580000102003920039200392003920039
80024200381500039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000502000416762003580000102003920039200392003920039
80024200381500083258001010800001080000506400000520019200382003899963100188001020800002080000200382003811800211091010800001000502050916342003580000102003920039200392003920039
80024200381500039258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001010502050916342003580000102003920039200392003920039
80024200381500039258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001000502050416442003580000102003920039200392003920039
80024200381500039258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001000502000816442003580000102003920039200392003920039
80024200381500039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000502050516782003580000102003920039200392003920039