Apple M1 Microarchitecture Research by Dougall Johnson

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

CMLT (zero, 8B)

Test 1: uops

Code:

  cmlt 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)03081e3f4e51inst 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
1004203716096116862510001000100026452112018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371501326116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmlt 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)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)60696b6d6edispatch 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)9fa6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500906119686251010010010000100100005002847521020018020037200371842861874110100200100082001000820037200371110201100991001001000010000001117180160019800100001002003820038200382003820038
10204200371500186119686251010010010000100100005002847521020018020037200371842871874010100200100082001000820037200371110201100991001001000010000001117170160019800100001002003820038200382003820038
1020420037150096119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010000000007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010000000007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010000000007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010000000007101161119791100001002003820038200382003820038
10204200371500576119686251010010010012100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010003000007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018020037200371842131874510100200100002001000020037200371110201100991001001000010000000007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018020037200371842131874510100200100002001000020037200371110201100991001001000010000000007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018020037200371842131874510100200100002001000020037200371110201100991001001000010000000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000075014719686251001010100001010152602847521120018200372003718443318767101632010000201000020037200371110021109101010000100000006402162219786010000102003820084200382003820038
1002420037150000000010319686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000001206119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000104000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150010000072619686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150010001206119686251001010100001010152502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000001206119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402242219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmlt v0.8b, v8.8b, #0
  cmlt v1.8b, v8.8b, #0
  cmlt v2.8b, v8.8b, #0
  cmlt v3.8b, v8.8b, #0
  cmlt v4.8b, v8.8b, #0
  cmlt v5.8b, v8.8b, #0
  cmlt v6.8b, v8.8b, #0
  cmlt 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): 0.2506

retire (01)cycle (02)0308181e1f3f51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420050150000050425801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801600200750800001002003920191200392003920039
8020420038150109047825801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010010111511801600200350800001002003920039200392003920039
802042003815000002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801600200350800001002003920039200392003920039
8020420038150000015725801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801600200350800001002003920039200392003920039
802042003815000002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010003111511801600200350800001002003920039200392003920039
802042003815000002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111512812311200450800001002004920050200502004920049
8020420048150000064268011610080016100800285006401960200282004920049997610998680128200800382008003820049200491180201100991001008000010020222512832311200450800001002004920050200502004920049
802042004815002006426801161008001610080028500640196020028200482004999769998680128200800382008003820048202001180201100991001008000010000222512812311200450800001002004920050200502004920050
802042004915000006426801161008001610080028500640196020028200482004899769998680128200800382008003820048200481180201100991001008000010000222512812311200460800001002004920050200502004920049
802042004815000006426801161008001610080028500640196020028200492004999769998680128200800382008003820048200481180201100991001008000010000222512812311200450800001002005020050200502004920049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308091e3f51inst 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)60696b6d6edispatch 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)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500003925800101080000108000050640000120019020038200389996310018800102080000208000020038200381180021109101080000100000050207162220035080000102003920039200392003920039
80024200381500003925800101080000108000050640000120019020038200389996310018800102080000208000020038200381180021109101080000100000050202162220035080000102003920039200392003920039
8002420038150000392580010108000010800005064000012001902003820038999631001880010208000020800002003820038118002110910108000010058300050202162220035080000102003920039200392003920039
80024200381500003925800101080000108000050640000120019020038200389996310018800102080000208000020038200381180021109101080000100000050206166220035080000102003920039200392003920039
80024200381500003925800101080000108000050640000120019020038200389996310018800102080000208000020038200381180021109101080000100000050202162220035080000102003920039200392003920039
80024200381500003925800101080000108000050640000120019020038200389996310018800102080000208000020038200381180021109101080000100000050202166220035080000102003920039200392003920039
80024200381500003925800101080000108000050640000120019020038200389996310018800102080000208000020038200381180021109101080000100000050202162220035080000102003920039200392003920039
8002420038150004053925800101080000108000050640000120019020038200389996310018800102080000208000020038200381180021109101080000100000050202166220035080000102003920039200392003920039
800242003815000070425800101080000108000050640000120019020038200389996310018800102080000208000020038200381180021109101080000100000050452162520035080000102003920039200392003920039
80024200381500003925800101080000108000050640000120019020038200389996310018800102080000208000020038200381180021109101080000100000050202162620035080000102003920039200392003920039