Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTAU (vector, 8H)

Test 1: uops

Code:

  fcvtau v0.8h, 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)03041e3a3f4e51inst 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
10043037230028225472510001000100039816003018303730372414328951000100010003037303711100110000377416442629100030383038303830383038
10043037231028225472510001000100039816003018303730372414328951000100010003037303711100110001077416442629100030383038303830383038
10043037241028225472510001000100039816003018303730372414328951000100010003037303711100110001377416442629100030383038303830383038
10043037241028225472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
10043037230028225472510001000100039816013018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
100430372410234325472510001000100039816013018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
10043037241028225472510001000100039816013018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
100430372300239125472510001000100039816013018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
10043037241028225472510001000100039816013018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
10043037231028225472510001000100039816013018303730372414328951000100010003037303711100110000077416442629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtau v0.8h, 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)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)9fa0a8a9acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071031622296330100001003003830038300383003830038
1020430037241061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
1020430037232061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372330105295472510100100100001001000050042771600300183003730037282643287451010020010000200106593003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
102043003723312612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000018071021622296330100001003003830038300383003830038
10204300372331261295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
1020430037232084295472510100100100001001000050042771601300183003730037282643287451010020010000200104903003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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)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)9fa8acc5cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250812954725100101010000101000050427716013001830037300372828603287671001020100002010000300373003711100211091010100001000064002162229629010000103003830038300383003830038
10024300372250612954725100101010000101000050427716013001830037300372828603287671001020100002010000300373003711100211091010100001000064002162229629010000103003830038300383003830038
10024300372250612954725100101010000101000050427716013001830037300372828603287671001020100002010000300373003711100211091010100001000064002162229629010000103008530181300863003830038
10024300372250612954725100101010000101000050427716013001830037300372828603287671001020100002010000300373003711100211091010100001000064002162229629010000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828603287671001020100002010000300373003711100211091010100001000064002162229629010000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828603287671001020100002010000300373003711100211091010100001000064002162229629010000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828603287671001020100002010000300373003711100211091010100001000064002162229629010000103003830038300383003830038
10024300372250612953825100101010000101000050427716013001830037300372828603287671001020100002010000300373003711100211091010100001000064002162229629010000103003830038300383003830038
10024300372250612954725100101010000101000050427716013001830037300372828603287671001020100002010000300373003711100211091010100001000064002162229629010000103003830038300383003830038
10024300372250612954725100101010000101000050427716013001830037300372828603287671001020100002010000300373003711100211091010100001000064002162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtau v0.8h, v8.8h
  fcvtau v1.8h, v8.8h
  fcvtau v2.8h, v8.8h
  fcvtau v3.8h, v8.8h
  fcvtau v4.8h, v8.8h
  fcvtau v5.8h, v8.8h
  fcvtau v6.8h, v8.8h
  fcvtau v7.8h, v8.8h
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)030918191e1f3f51inst 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)9fa6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006715500000402580108100800081008002050064013212014020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040
80204200391550001203025801081008000810080020500640132120020200392003999866100438012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040
802042003915500000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040
802042003915500000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040
802042003915500000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040
802042003915500000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001002000111511801600200360800001002004020040200402004020040
802042003915500000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000100111511801600200360800001002004020040200402004020040
802042003915500000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040
802042003915500000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040
8020420039155000001252580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080b18191e3f51inst 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)9fa0a1a6a7a8a9acc2cfd5d6daddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039155000000230258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000005020216043200360080000102004020040200402004020040
800242003915500000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000005020316034200360080000102004020040200402004020040
800242003915500000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000005020716044200360080000102004020040200402004020040
800242003915500000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000005020416043200360080000102004020040200402004020040
800242003915500000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000005020416077200360080000102004020040200402009320040
800242003915500000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000005020416043200360080000102004020040200402004020040
800242003915500000040258001010800001080000506400000200202003920039999631001980010208000020800002003920042118002110910108000010000000005020316043200360080000102004020040200402004020040
800242003915600000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000005020416046200360080000102004020040200402004020040
800242003915500000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000005020416034200360080000102004020040200402004020040
800242003915500000081258001010800001080000506400000200202024520039999631001980010208000020800002003920039118002110910108000010000000005020416043200361080000102004020040200402004020040