Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTZU (vector, fixed-point, 2D)

Test 1: uops

Code:

  fcvtzu v0.2d, v0.2d, #3
  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)0318191e3f4e51inst 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
10043037240006125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
10043037230006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372300010325472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037231006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240006125472510001000100039816013018303730372414328951000100010003084303711100110000073116112629100030383038303830383038
100430372300010325472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013018303730842414328951000100010003037303711100110000073116112629100030383038303830383038
10043037241006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzu v0.2d, v0.2d, #3
  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)0318191e3a3f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330000662954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037331102011009910010010000100000710117112963325100001003003830086300383003830038
102043003723200006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000710116112963325100001003003830038300383003830038
10204300372330000612954725101001001000010010000626427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372330000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372330001612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010012071001611296330100001003003830038300383003830038
10204300372330000612954725101251001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000075611611296330100001003003830038300383003830085
10204300372330000612954725101251001000712510000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071411611296330100001003003830038300383003830038
10204300372330000612954725101001001000010010000626427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071411611296330100001003003830038300383003830038
10204300372330000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071411611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308181e3f4e51inst 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
100243003722500031229547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100006405165429629010000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100006404165529629010000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100006405165529629010000103003830038300383003830038
100243003722500019129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100006404165429629010000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100006404165429629010000103003830038300383003830038
10024300372250006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006405164529629010000103003830038300383003830038
100243003722500016829547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100006405164529629010000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100006405165429629010000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100006404164529629010000103003830038300383003830038
100243003722500018929547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006405165429629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzu v0.2d, v8.2d, #3
  fcvtzu v1.2d, v8.2d, #3
  fcvtzu v2.2d, v8.2d, #3
  fcvtzu v3.2d, v8.2d, #3
  fcvtzu v4.2d, v8.2d, #3
  fcvtzu v5.2d, v8.2d, #3
  fcvtzu v6.2d, v8.2d, #3
  fcvtzu v7.2d, v8.2d, #3
  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)03080b18191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060156000090030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000006011151180160020036800001002004020040200402004020040
80204200391550000360030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
8020420039155001000030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
802042003915500002700345638010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040202452004020040
80204200391560100360030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
80204200391551000000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000001015011151180160020036800001002004020040200402004020040
80204200391550000210030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
80204200391560000210030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
8020420039156000060030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e1f3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002520039155000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010035020316342003680000102004020040200402004020040
80024200391550002722580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020316452003680000102004020040200402004020040
8002420039155000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020316442003680000102004020040200402004020040
8002420039155000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020316352003680000102004020040200402004020040
8002420039156000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020516342003680000102004020040200402004020040
8002420039155000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020516442003680000102004020040200402004020040
8002420039161000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020316342003680000102004020040200402004020040
8002420039155000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005059416542003680000102004020040200402004020040
8002420039155000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010035020416542003680000102004020040200402004020040
80024200391550002302580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020416442003680000102004020040200402004020040