Apple M1 Microarchitecture Research by Dougall Johnson

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

FMINNMV (8H)

Test 1: uops

Code:

  fminnmv h0, v0.8h
  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)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
10043037230126254725100010001000398160030183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
10043037233355254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037223612547251000100010003981600301830373037241432895100010001000303730371110011000001873116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100030073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100010073116112629100030383038303830383038
1004303722065254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100004373116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100040373116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fminnmv h0, v0.8h
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225001682954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000710316222963319100001003003830038300383003830038
10204300372240061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003013430038300383003830038
10204300372250061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
102043003722500145295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
102043003722500147295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372240061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250003924616457229484154100671310048131105065428662403027030366303682831203528899109122210991221114930368300379110021109101010000100220141675307895723329878210000103041730370303693036830323
10024303592250127936616456129482159100611710056151105076428256803027030366303702831203228900110632410986241098230401303689110021109101010000100201221962028083414329847210000103041730320302153037030370
100243032222610719336165199294841721007314100561511032654277160130234303693036728312038289121106620111532111475304143046410110021109101010000100000022241006834834329907210000103046130466304653041630417
100243041422810281065704578929529175100771210072131045071428950903012630451304512831103928930112132211305281131330462304605110021109101010000102030022493028303723229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010000000006402162229629110000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10025300372250000009429547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fminnmv h0, v8.8h
  fminnmv h1, v8.8h
  fminnmv h2, v8.8h
  fminnmv h3, v8.8h
  fminnmv h4, v8.8h
  fminnmv h5, v8.8h
  fminnmv h6, v8.8h
  fminnmv h7, v8.8h
  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)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)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)9facc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611500695258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001003322251292231120045800001002004920049200502005020049
802042004815006427801161008001610080028500640196200292004820048997699986801282008003820080038200482004811802011009910010080000100022251291231120045800001002004920049200502004920050
8020420049150011026801161008001610080028500640196200292004820048997699986801282008003820080038200492004811802011009910010080000100022251292231120169800001002005020050200502005020049
802042004915006427801161008001610080028500640196200292004820048997699986801282008003820080038200482004811802011009910010080000100022251291231120045800001002004920050200502005020049
8020420048150064268011610080016100800285006401962002920048200489976109986801282008003820080038200482004811802011009910010080000100022251281231120045800001002004920049200492004920049
802042004815506426801161008001610080028500640196200292004920048997699986801282008003820080038200482004911802011009910010080000100022251281231120045800001002005020049200492004920049
8020420048150064278011610080016100800285006401962002920048200489976109986801282008003820080038200482004811802011009910010080000100022251291231120045800001002005020049200492005020050
8020420048150081426801841008001610080028500640196200292004820048997699986801282008003820080038200482004811802011009910010080000100022251282231120046800001002004920050200492004920050
802042004915006427801161008001610080028500640196200292004920048997699986801282008003820080038200482004911802011009910010080000100022251291231120045800001002005020049200492005020049
8020420049151064268011610080016100800285006401962002920048200489976109986801282008003820080038200482004911802011009910010080000100022251291231120045800001002004920050200492004920049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3f51inst 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)9fa0a1a6a7a8a9acc2cfd0d5d6ddinst fetch restart (de)dfe0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000000005024311611320036080000102004020040200402004020040
8002420039150000000776258001010800001080000506400001200202003920039999631004780010208000020800002003920039118002110910108000010000000005024311611320036280000102004020040200402004020040
800242003915000000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000000005024311611320036080000102004020040200402004020040
800242003915000000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000000005024311611320036080000102004020040200402004020040
800242003915500000040258001010800001080000506400001200202003920039999661001980116208000020800002003920039118002110910108000010000000005024311611320036080000102004020040200402004020040
800242003915000000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000000005024321611320036080000102004020040200402004020040
8002420039150000012040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000000005024311611320036080000102004020040200402004020040
800242003915000010040258010710800961080000506408360200202003920039999631001980010208000020800002003920039118002110910108000010000000305024312612320036080000102004020040200402004020040
800242003915000000082258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000000005024311611320036080000102004020040200402004020040
800242003915000000040258001010800001080105506400001200202003920039999631001980010208000020800002003920039118002110910108000010000000005024311611320036080000102004020040200402004020040