Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINT64Z (scalar, S)

Test 1: uops

Code:

  frint64z 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)030b1e3f4e51inst 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
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
10043037230126125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372400103254725100010001000398160030183037303724143289510001000100030373037111001100002173116112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100001873116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723036125472510001000100039816013018303730372414328951000100010003037303711100110004073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230061254725100010001000398160130183037303724143289510001000100030373037111001100002173116112629100030383038303830383038
10043037240061254725100010001000398160030183037303724143289510001000100030373037111001100001873116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frint64z 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)030b18191e1f3f4e51inst 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)9fa1a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300021061295472510100100100001001000050042771601300180300373003728264328745101002041000021410000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038
102043003723300000124295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038
10204300372330000089295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038
102043003723200000166295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038
10204300372320000061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038
10204300372320000061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100001000710011611296330100001003003830038300383003830038
102043003724300000103295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100000090710011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e1f3f4e51inst 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)9fa0a6a7a8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372330000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006403162229629010000103003830038300383003830038
10024300372320000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372330000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037233000001120295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037233000001053295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001002000006402162229629010000103003830038300383003830038
100243003723300000923295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037233000002320295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037233000001202295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003724100000277295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037233000301059295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001020000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frint64z s0, s8
  frint64z s1, s8
  frint64z s2, s8
  frint64z s3, s8
  frint64z s4, s8
  frint64z s5, s8
  frint64z s6, s8
  frint64z 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)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)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)9fa0a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391560000074258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915500200695258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391640000030258010810080008100801285006401320200202017220197998769990801202008003220080038200392003911802011009910010080000100000311151180160020036800001002004020040200402004020040
80204200391560000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391550000058258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
8020420039155000026430258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391550000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181160020036800001002004020040200402004020040
80204200391550000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020155800001002004020040200402004020040
802042003915500012030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100010011151180160020036800001002004020040200402004020040
80204200391550000072258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080b18191e1f3f51inst 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)9fa0a1a6a7a8acc2c5cfd0d2d5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391550000000402580010108000010800005064000015200202003920039999631001980010208000020800002003920039118002110910108000010000000005020501168112003680000102004020040200402004020040
800242003915500000001242580010108000010800005064000015200202003920039999631004780319208000020800002003920039118002110910108000010000000005020501168112003680000102004020040200402004020040
80024200391550000000402580010108000010800005064000015200202003920039999631001980010208000020800002003920039118002110910108000010000000005020501166112003680000102004020040200402004020040
80024200391550000000402580010108000010800005064000015200202003920039999631001980010208000020800002003920039118002110910108000010000000005020501166112003680000102004020040200402004020040
80024200391550000000402580010108000010800005064000015200202003920039999631001980010208000020800002003920039118002110910108000010000000005020501166112003680000102004020040200402004020040
80024200391550000000402580010108000010800005064000015200202003920039999631001980010208000020800002003920039118002110910108000010000000015020501168112003680000102009020040200402004020040
80024200391550000000402580010108000010800005064000015200202003920039999631004680122208000020800002003920039118002110910108000010000000005020501166112003680000102004020040200402004020040
800242003915600000120402580010108000010800005064000015200202003920039999631001980010208000020800002003920039118002110910108000010000000005020501168112003680000102004020040200402004020040
80024200391550000000402580010108000010800005064000015200202003920039999631001980010208000020800002003920039118002110910108000010000000005020501166112011680000102004020040200402004020040
8002420039155000000011372580010108000010800005064000015200202003920039999631001980010208000020800002003920039118002110910108000010000006005020511168112003680000102004020040200402004020040