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, 4H)

Test 1: uops

Code:

  fcvtau v0.4h, v0.4h
  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)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
1004303723015625472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723246125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372408225472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723010325472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372466125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtau v0.4h, 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): 3.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9d9fa0a1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100000100000071021622296330100001003003830038300383003830038
102043003723300612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100000100003071021622296330100001003003830038300383003830038
102043003723300612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100000100008971021632296330100001003003830038300383003830038
102043003724100612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100000100000071021622296330100001003003830038300383003830038
1020430037232001032954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100000100001071021622296330100001003003830038300383003830038
102043003723300612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100000100000071021622296330100001003003830038300383003830038
1020430037232120612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100000100000071021622296330100001003003830038300383003830038
1020430037232006129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000001000031371021622296330100001003003830038300383003830038
102043003723300612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100000100000071021622296330100001003003830038300383003830038
102043003724100612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100000100000071021622296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e3f4e51inst 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)9fa1a6a8a9accfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000006402162229701010000103003830038300383003830133
1002430037224006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000001626402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000846402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000816402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000876402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000846402162229629010000103003830038300383003830038
1002430037241006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000036402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001803003730037282863287671001020100002010000300373003711100211091010100001000001146402162229629010000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000036402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtau v0.4h, v8.4h
  fcvtau v1.4h, v8.4h
  fcvtau v2.4h, v8.4h
  fcvtau v3.4h, v8.4h
  fcvtau v4.4h, v8.4h
  fcvtau v5.4h, v8.4h
  fcvtau v6.4h, v8.4h
  fcvtau v7.4h, v8.4h
  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)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)9fa0a1a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058156030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181160020036800001002004020040200402004020040
8020420039155051258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
8020420039156030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
8020420039155030258010810080008100800205006401320201002003920039997769990801202008003220080032200392015021802011009910010080000100000311151180160020036800001002004020040200402004020040
80204200391550512580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000019111520211232220045800001002004920050200492004920049
8020420048155064278011610080016100800285006401960200292004920048997699986801282008003820080038200492004811802011009910010080000100000022251281231120045800001002004920050200492005020049
80204200491550642680116100800161008002850064019602002920048200489976109986801282008003820080038200482004811802011009910010080000100000022251291341120045800001002005020049200492005020050
80204200491566106268011610080016100800285006401960200292004820048997699986801282008003820080038200492004811802011009910010080000100000022251281231120046800001002004920049200492004920050
8020420048156064278011610080016100800285006401960200292004820048997699986801282008003820080038200482004811802011009910010080000100000022251281231120045800001002005020049200492004920049
8020420048155064278011610080016100800285006401961200292004920048997699986801282008003820080038200482004811802011009910010080000100000022251281231120046800001002005020050200492004920050

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030818191e1f3f51inst 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)6061696d6edispatch 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)93inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8a9accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115600000402580010108000010800005064000000200202003920039999603100198001020800002080000200392003911800211090101080000100000005020071635200360080000102004020040200402004020040
8002420039161000002112580010108000010800005064000000200202003920039999603100198001020800002080000200392003911800211090101080000100000005020031655200360080000102004020040200402004020040
800242003915500000402580010108000010800005064000000200202003920039999603100198001020800002080000200392003911800211090101080000100000005020051635200360080000102004020040200402004020040
800252003915500000402580010108000010800005064000000200202003920039999603100198001020800002080000200392003911800211090101080000100000005020031635200360080000102004020040200402004020040
800242003915500000402580010108000010800005064000000200202003920039999603100198001020800002080000200392003911800211090101080000100000005020041653200360080000102004020040200402004020040
800242003915500000402580010108000010800005064000000200202003920039999603100198001020800002080000200392003911800211090101080000100000005020051655200360080000102004020040200402004020040
800242003915600000402580010108000010800005064000000200202003920039999603100198001020800002080000200392003911800211090101080000100000005020031645200360080000102004020040200402004020040
800242003915500000402580010108000010800005064000000200202003920039999603100198001020800002080000200392003911800211090101080000100000005020051653200360080000102004020040200402004020040
80024200391610000081725800101080000108000050640000002002020039200399996031001980010208000020800002003920039118002110922101080000100008065020051655200360080000102004020040200402004020040
800242003915500000402580010108000010800005064000000200202003920039999603100198001020800002080000200392003911800211090101080000100000005020051653200360080000102004020040200402004020040