Apple M1 Microarchitecture Research by Dougall Johnson

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

CMGT (zero, 4H)

Test 1: uops

Code:

  cmgt v0.4h, v0.4h, #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)033f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371561168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371661168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371561168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371561168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371561168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371561168625100010001000264521020182037203715713189510001000100020372037111001100040073116111786100020382038203820382038
100420371561168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371561168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371561168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371561168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmgt v0.4h, v0.4h, #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)9fa1a8c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119686251010010010000100100005002847521120018200372003718428718740101002001000820010008200372003711102011009910010010000100001117181161119800100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718428618741101002001000820010008200372003711102011009910010010000100001117181161119801100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718428618741101002001000820010008200372003711102011009910010010000100001117171161119801100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718428718740101002001000820010008200372003711102011009910010010000100001117181161119801100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
1020420037150276119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
102042003715006119686251010010010000124100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03091e1f3f4e51inst 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)72scheduler 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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500240187196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000100640316331978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000100640316331978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000100640316331978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000100640316331978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000100640316331978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000100640316331978610000102003820038200382003820038
1002420037150021061196862510010101000010100005028475211200182003720037184437318767100102010000201000020037200371110021109101010000100640316331978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000100640316331978610000102003820038200382003820038
100242003715010061196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000100640316331978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184430318767100102010000201000020037200371110021109101010000100640316331978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmgt v0.4h, v8.4h, #0
  cmgt v1.4h, v8.4h, #0
  cmgt v2.4h, v8.4h, #0
  cmgt v3.4h, v8.4h, #0
  cmgt v4.4h, v8.4h, #0
  cmgt v5.4h, v8.4h, #0
  cmgt v6.4h, v8.4h, #0
  cmgt v7.4h, v8.4h, #0
  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)0308091e1f3f51inst 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
80204200571500000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181160020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500060292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150000132292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815000150292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030708090a0b18191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150000000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020616562003580000102003920039200392003920039
8002420038150000000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020316322003580000102003920039200392003920039
8002420038150000000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000030005020516632003580000102003920039200392003920039
8002420038150000000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000020005020516362003580000102003920039200392003920039
8002420038150000000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020316332003580000102003920039200392003920039
8002420038150000000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000010005020316352003580000102003920039200392003920039
8002420038150000000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000305020216332003580000102003920039200392003920039
8002420038150000000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020816232003580000102003920039200392003920039
8002420038150000000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000010005020316552003580000102003920039200392003920039
8002420038150000000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020216232003580000102003920039200392003920039