Apple M1 Microarchitecture Research by Dougall Johnson

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

CMLE (zero, 8H)

Test 1: uops

Code:

  cmle v0.8h, v0.8h, #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)031e1f3f4e51inst 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
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073216111786100020382038203820382038
1004203716008216862510001000100026452102018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715008216862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmle v0.8h, v0.8h, #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)9fa6cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715001471968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101241119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500891968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715008121968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000611968625100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000611968625100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000611968625100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000611968625100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000611968625100101010000101000050284752102001802003720037184433187851001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000711968625100101010000101000050284752102001802003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000611968625100101010000101000050284752102001802003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000611968625100101010000101000050284752102001802003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000611968644100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000611968644100101010000101000050284752112001802003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmle v0.8h, v8.8h, #0
  cmle v1.8h, v8.8h, #0
  cmle v2.8h, v8.8h, #0
  cmle v3.8h, v8.8h, #0
  cmle v4.8h, v8.8h, #0
  cmle v5.8h, v8.8h, #0
  cmle v6.8h, v8.8h, #0
  cmle v7.8h, v8.8h, #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)03091e3a3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715010029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151182161220035800001002004920049200492004920049
8020420049151000642680116100800161008002850064019620028200492004899761099868012820080038200800382004820048118020110099100100800001000022251283232320046800001002004920049200492004920049
802042004815000064278011610080016100800285006401962002820048200489976999868012820080038200800382004920048118020110099100100800001000022251291233420045800001002004920049200492004920049
80204200491500002542680116100800161008002850064019620028200482008699761099868012820080038200800382004820048118020110099100100800001000022251292233220045800001002005020049200492004920049
8020420049150000642780116100800161008002850064019620028200492004999761099868012820080038200800382004820049118020110099100100800001000022251282232320045800001002004920050200502004920050
802042004815000064268011610080016100800285006401962002820048200489976999868012820080038200800382004920049118020110099100100800001000022251282233320045800001002004920049200492004920050
802042004915000064278011610080016100800285006401962002820048200489976999868012820080038200800382004820049118020110099100100800001000022251282232320045800001002004920049200502004920049
8020420049150000642680116100800161008002850064019620028200492004999761099868012820080038200800382004820048118020110099100100800001001022251282233220046800001002004920049200492004920049
802042004815000064268011610080016100800285006401962002820049200499976999868012820080038200800382004920049118020110099100100800001000022251283233220046800001002004920049200492004920049
802042004815000064278011610080016100800285006401962002820049200489976999868012820080038200800382004820048118020110099100100800001000022251283232220046800001002004920050200492005020050

1000 unrolls and 10 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020416532003580000102003920039200392003920039
80024200381500324258001010800001080000506400000200792003820038999631001880010208000020800002003820038118002110910108000010005020516532003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020516532003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020516552003580000102003920039200392003920039
80024200381501539258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020316532003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005037516352003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020516352003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010035020316352003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020616552003580000102003920039200392003920039
8002420038150639258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020516552003580000102003920039200392003920039