Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTZU (scalar, integer, D to D)

Test 1: uops

Code:

  fcvtzu d0, d0
  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)031e1f3f4e51inst 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)a0a1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303725906125472510001000100039816013018303730372414328951000100010003084303711100110002200073316222629100030383038303830383038
10043037231206125472510001000100039816013018303730372414328951000100010003037303711100110000000073216222629100030743085303830383038
10043037240886125472510001000100039816013018303730372414328951000100010003037303711100110000010073216222629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000000073216222629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000000073216222629100030383038303830383038
1004303724306125472510001000100039816013018303730372414328951000100010003037303711100110000000073216222629100030383038303830383038
1004303724006125472510001000100039816013018303730372414328951000100010003037303711100110000000073216222629100030383038303830383038
10043037241206125472510001000100039816013018303730372414328951000100010003037303711100110000003073216222629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000000073216222629100030383086303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003084303711100110000000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzu d0, d0
  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)03090b191e3f4e51inst 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000040071013311296330100001003003830038300383003830038
10204300372330000103295472510100100100001001000050042771601301623003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037233000061295472510100100100081001000050042771600300183003730037282643287451010020010000200106643023030037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037233000089295472510100100100001001000050042771601300183012230085282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003723300006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100002230710116112963317100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000010071011611296330100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000010071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000612954725100101010000101000050427716030018300373003728286328767100102010000201016330084300371110021109101010000100001006402162229629010000103003830038300383003830038
100243003722500000007262954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000066402162229629010000103003830038300383003830038
100243003722500000007262954725100101110000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000036402162229629010000103003830038300383003830038
10024300372240000000612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372250000001612954725100101010000101000050427716030018300373003728286328767100102210000201000030037300371110021109101010000100000036402162229629010000103003830038300383003830038
1002430037224000000072629547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000018006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000102401006402162229629010000103003830038300383003830038
10024300372240000000612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100002006402162229629010000103003830038300383003830038
100243003722500000004532954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100031006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzu d0, d8
  fcvtzu d1, d8
  fcvtzu d2, d8
  fcvtzu d3, d8
  fcvtzu d4, d8
  fcvtzu d5, d8
  fcvtzu d6, d8
  fcvtzu d7, d8
  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)0308191e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd0d2d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059155000302580108100800081008002050064013210200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118001620036800001002004020040200402004020040
8020420039156000302580108100800081008002050064013200200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118001620036800001002004020040200402004020040
80204200391550001812580108100800081008002050064013200200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118001620036800001002004020040200402004020040
80204200391550001162580108100800081008002050064013200200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118001620036800001002004020040200402004020040
80204200391560001162580108100800081008002050064013200200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118001620036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013200200202003920039997769990801202008003220080032200392003911802011009910010080000100101115118001620036800001002004020040200402004020040
80204200391550004082580108100800081008002050064013200200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118001620036800001002004020040200402004020040
80204200391560004522580108100800081008002050064013200200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118001620036800001002004020040200402004020040
8020420039156000302580108100800081008002050064013200200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118001620036800001002004020040200402004020040
8020420039161000302580108100800081008002050064013200200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118001620036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0309181e1f3f51inst 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)5f6061696d6edispatch 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)9fa8accfd5d6dbddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039155000040258001010800001080000506400000002002020039200399996031001980010208000020800002003920039118002110910108000010005020716024200364080000102004020040200402004020040
8002420039155000022025800101080000108000050640000000200202003920039999603100198001020800002080000200392003911800211091010800001000502041604420036080000102004020040200402004020040
80024200391560000102825800101080000108000050640000000200202003920039999603100198001020800002080000200392003911800211091010800001000502071604720036080000102004020040200402004020040
800242003915500004025800101080000108000050640000010200202003920039999603100198001020800002080000200392003911800211091010800001000502041602420036080000102004020040200402004020040
800242003915500004025800101080000108000050640000000200202003920039999603100198001020800002080000200392003911800211091010800001000502021604220036080000102004020040200402004020040
800242003915500004025800101080000108000050640000100200202003920039999603100198001020800002080000200392003911800211091010800001000502021604220036080000102004020040200402004020040
800242003915500004025800101080000108000050640000000200202003920039999603100198001020800002080000200392003911800211091010800001000502041604420036080000102004020040200402004020040
8002420039156000048625800101080000108000050640000000200202003920039999603100198001020800002080000200392003911800211091010800001000502021602420036080000102004020090200402004020040
800242003915500004025800101080000108000050640000000200202003920039999603100198001020800002080000200392003911800211091010800001000502021603420036080000102004020040200402004020040
800242003915600004625800101080000108000050640000000200202003920039999603100198001020800002080000200892003911800211091010800001000502041602420036080000102004020040200402004020040