Apple M1 Microarchitecture Research by Dougall Johnson

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

CMTST (register, 4H)

Test 1: uops

Code:

  cmtst v0.4h, v0.4h, v1.4h
  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)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371606116872510001000100026468020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371606116872510001000100026468020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371508216872510001000100026468020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
1004203715012416872510001000100026468020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371608216872510001000100026468020182037203715723189510001000200020372037111001100000073216221803100020382038203820382038

Test 2: Latency 1->2

Code:

  cmtst v0.4h, v0.4h, v1.4h
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150018105196872510100100100001001000050028476800200182003720037184223187451010020010000200203442003720037111020110099100100100001002971011611197910100001002003820038200382003820038
10204200371500151051968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010036371011611197910100001002003820038200382003820038
102042003715001561196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371501084196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715009611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010001571011611197910100001002003820038200382003820038
10204200371501061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001002071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080a0b18191e1f3a3f4e51inst 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)696d6edispatch 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715010100000268196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006441016101019785010000102003820038200382003820038
100242003715010100000268196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006448168519785010000102003820038200382003820038
100242003715010100000268196872510010101000010100005028476802001820037200371844431876710163201000020203242008420084111002110910101000010000000006441016101019785010000102003820038200382003820038
100242003715010100000268196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006441016101019785010000102003820038200382003820038
100242003715010100000268196872510010101000010100005028480062001820037200371844431876710010201000020200002003720037111002110910101000010000000006441016101019785010000102003820038200382003820038
10024200371501010000026819687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000000644111610519785010000102003820038200382003820038
10024200371501010009026819687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000002201806441116111019785010000102003820038200382003820038
10024200371501010000026819687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000012306441016111019785010000102003820038200382003820038
10024200371501010000026819687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000012064461651119785010000102003820038200382003820038
100242003715010100000268196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006441016101019785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmtst v0.4h, v1.4h, v0.4h
  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)0308091e3f4e51inst 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)9fa8acc5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150009841968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420084150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420085150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010010007101161119791100001002003820038200382003820038
10204200371500001241968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500101031968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500001701968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500001261968725101001001000010010000500284768002001820037200371842231874510433200100002002000020037200851110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b191e1f3a3f4e51inst 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)696d6edispatch 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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500100001241968725100101010000101015050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640416441982410000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640416441978510000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100130640416431978510000102003820038200382003820038
10024200371500000003491968725100101010000101000050284768020018200372003718444318767100102010180202000020037200371110021109101010000100130640316441978510000102003820038200382003820038
10024200371500000003521968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000102000640416441978510000102003820038200382003820038
10024200371500000002531968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640316431978510000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640416441978510000102003820038200382003820038
10024200371500000004581968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000668416431978510000102003820038200382003820038
1002420037150100000841968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640416431978510000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640416341978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmtst v0.4h, v8.4h, v9.4h
  cmtst v1.4h, v8.4h, v9.4h
  cmtst v2.4h, v8.4h, v9.4h
  cmtst v3.4h, v8.4h, v9.4h
  cmtst v4.4h, v8.4h, v9.4h
  cmtst v5.4h, v8.4h, v9.4h
  cmtst v6.4h, v8.4h, v9.4h
  cmtst v7.4h, v8.4h, v9.4h
  movi v8.16b, 9
  movi v9.16b, 10

(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)9fa8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915001542580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100002051102161220035800001002003920039200392003920039
802042003815002222580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101301120035800001002003920039200392003920039
802042003815006832580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500402580100100800001148000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500842580100100800001008009950064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003814915402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000151101161120035800001002003920039200392003920039
80204200381500902580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304091e3a3f51inst 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)9fa8accfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500100392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005021000118160001818200350080000102003920039200392003920039
80024200381501000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005021000114160001714200350080000102003920039200392003920039
800242003815010150392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005021000113160001714200350080000102003920039200392003920039
800242003815010002292580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005021000117160001417200350080000102003920039200392003920039
80024200381500000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005021000117160001617200350080000102003920039200392003920039
8002420038150100039258001010800001080000506400001200192003820090999631001880010208000020160000200382003811800211091010800001000502100019160001714200350080000102003920039200392003920039
80024200381501000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005021000117160001817200350080000102003920039200392003920039
8002420038150100039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000502100018160001714200350080000102003920039200392003920039
80024200381501000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005021000114160001714200350080000102003920039200392003920039
80024200381501000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005021000114160001714200350080000102003920039200392003920039