Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTZS (scalar, integer, H to H)

Test 1: uops

Code:

  fcvtzs h0, h0
  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)03191e3f4e51inst 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)a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100003073116112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300103254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430852400612547251000100010003981600301830373037241432895100010001000303730371110011000012073116112629100030383038303830383038
10043037250061254725100010001000398160030183037303724143289510001000100030373037111001100013073116112629100030383038303830383038
10043037240061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300251254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037240061254725100010001000398160130183037303724143289510001000100030373037111001100010073116112629100030383038303830383085

Test 2: Latency 1->2

Code:

  fcvtzs h0, h0
  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)0307080b18191e1f3f4e51inst 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)9fa6a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000002706129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225000002106129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722510000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000171011611296330100001003003830038300383003830038
102043003722500000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722400000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225000401506129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225100001506129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b181e1f3f4e51inst 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
10024300372250001921682954725100101010000101015050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372240000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010106402162229773010000103003830038300383003830038
10024300372250000842954725100101010000101000050427716003001830037300842828632876710010201000020100003003730037111002110910101000010036402162229629010000103003830038300383003830038
100243003722502452641912954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250001767262954743100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006402162229703010000103003830038300383003830038
10024300372250000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzs h0, h8
  fcvtzs h1, h8
  fcvtzs h2, h8
  fcvtzs h3, h8
  fcvtzs h4, h8
  fcvtzs h5, h8
  fcvtzs h6, h8
  fcvtzs h7, h8
  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)0307080b18191e1f3f51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000000120722580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
80204200391500000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000030111511801600200360800001002004020040200402004020040
80204200391500000000722580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001000211511801600200360800001002004020040200402004020040
8020420039150000003930302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
802042004915010000006445801161008001610080028500640196020029200482004899761099868012820080038200800382015320048418020110099100100800001000000030222512912311200450800001002004920050200502004920049
802042004916100000001062680116100800161008002850064019602002920048200489976109986801282008003820080038200492004811802011009910010080000100000001950222512812311200450800001002004920049200502004920049
80204200481500000000852780116100800161008002850064019602002920049200489976999868012820080038200800382004820048118020110099100100800001000000000222512812311200460800001002004920049200492004920049
80204200481500000000642680195100800161008002850064019602002920048200489976999868012820080038200800382004920048118020110099100100800001000000000222512812311200450800001002004920049200502005020049
80204200481500000000642680116100800161008002850064019602002920049200489976999868012820080038200800382004820049218020110099100100800001000000060222512812311200450800001002004920050200502005020050
802042004815000000001482680116100800161008002850064019602002920048200491000210998680128200800382008003820048200481180201100991001008000010000000270222512912311200450800001002005020049200492005020049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b181e3f51inst 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)5f60696d6edispatch 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015600007262580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010000050204163420059080000102004020040200402004020040
800242003915500093642580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010000050207164420036080000102004020040200402004020040
800242003916100001872580010108000010800005064000011200202003920039999631004680010208000020800002003920039118002110910108000010000050203167620036080000102004020040200402004020040
80024200391501000402580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010000050203163420036080000102004020040200402004020040
80024200391500000402580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010000050204164720036080000102004020040200402004020040
800242003915000001872580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010000050206164320036080000102004020040200402004020040
800242003915000002192580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050204164320036080000102004020040200402004020040
80024200391500000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050203163420036080000102004020040200402004020040
80024200391500000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000950204164320036580000102004020040200402004020040
80024200391500000402580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010000050203165420036080000102004020040200402004020040