Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTAU (scalar, S to S)

Test 1: uops

Code:

  fcvtau s0, s0
  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)030818191e1f3f4e51inst 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
10043037240002408225472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724000006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724000006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723000006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230004506125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724000008225472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723000006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723000006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240003306125472510001000100039816013018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
1004303724000006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtau s0, s0
  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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723206129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373008411102011009910010010000100490071021622296330100001003003830038300383003830038
10204300372331261295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000180071021622296330100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160030018300373003728264328745101002061000020010165300373003731102011009910010010000100712471023222296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000132071021622296330100001003003830038300383003830038
1020430037233061295382510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000132071021622296330100001003003830038300383003830038
1020430037232061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000123071021622296330100001003003830038300383003830038
10204300372331226762954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010036071021622296330100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100420071021622296330100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100530071021622296330100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100473071021622296330100001003003830038300383003830038

1000 unrolls and 10 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225001912954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010473640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010159640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010486640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010539640216222962910000103003830038300383003830038
100243003722400612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010430640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010509640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010449640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010473640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010536640216222962910000103003830038300383003830038
100243003722400612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010212640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtau s0, s8
  fcvtau s1, s8
  fcvtau s2, s8
  fcvtau s3, s8
  fcvtau s4, s8
  fcvtau s5, s8
  fcvtau s6, s8
  fcvtau s7, s8
  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)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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391550302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915506952580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915512302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391560302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180161120036800001002004020040200452009120040
80204200391610302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b18191e1f3a3f51inst 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)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)9fa0a6a7a8a9acc2cfd0d2d5d6d9dbddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501560000000040258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000026030502000516004320036080000102004020040200402004020040
8002420039155000000004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100000000502000416007620036080000102004020040200402004020040
8002420039156000000004025800101080000108000050640000002002020039200399996310019800102080000208010320039200392180021109101080000100004000502000616004420036080000102004020040200402004020040
80024200391550000012004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100002000502000616404720036080000102004020040200402004020040
80024200391550000000040258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000000990502000416004420036650280000102004020040200402004020040
80024200391600000000061025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100001000502000416007620036080000102004020040200402004020040
800242003915500000000402580010108000010800005064000010200202003920039999631001980010208000020800002003920039118002110910108000010000001170502000616004720036080000102004020040200402004020040
80024200391550000000040258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000028000502000416003420036080000102004020040200402004020040
80024200391550000000040258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000038000502000316004720036080000102004020040200402004020040
8002420039155000000004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100004201800502000416007620036080000102004020040200402004020040