Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTP (vector, 2D)

Test 1: uops

Code:

  frintp v0.2d, v0.2d
  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)03191e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723066125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303724006125472510001000100039816030183037303724143289510001000100030373037111001100000073216222699100030383038303830383038
1004303723006125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303723006125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303723006125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303723006125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372302110325292510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303724006125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
10043037240126125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303723006125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintp v0.2d, v0.2d
  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)0308090b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330000000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000030710116112963300100001003003830038300383003830038
10204300372330000000061295472510100100100001001015057142771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000710116312963300100001003003830038300383003830038
102043003723200000000265295472510100100100001001000050042771601300183003730037282743287451010020010000200100003003730037111020110099100100100001000000002710124322963300100001003008530038300383003830325
10204300372331000000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000710116112963300100001003003830038300383003830038
1020430037233100003988061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000710116112963330100001003003830038300383003830038
102043003723300000000231295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000001060710116122963300100001003003830038300383003830038
10204300372330000000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003008430037111020110099100100100001000000000710116112963300100001003003830038300383003830038
1020430037233000000006129547251010010010000100100005224277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000106071011611296330135100001003003830038300383003830038
102043003723300000000840295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000710116112963300100001003003830038300383003830038
10204300372330000000061295472510100100100001001000050042771601300183003730037282643287451010020010000202100003003730037111020110099100100100001002000000710116112963300100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)9fa1a6a7a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250045061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
1002430037224000061295472510010131000010100005042771601300180300373003728285328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
1002430037225000061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
1002430037224000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
1002430037225000061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
1002430037225000061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000000640217222962910000103003830038300383003830038
10024300372250000147295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
1002430037225000061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
1002430037225000061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
1002430037225000061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintp v0.2d, v8.2d
  frintp v1.2d, v8.2d
  frintp v2.2d, v8.2d
  frintp v3.2d, v8.2d
  frintp v4.2d, v8.2d
  frintp v5.2d, v8.2d
  frintp v6.2d, v8.2d
  frintp v7.2d, v8.2d
  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)0307080b18191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042008915500000120010332580108100800081008002050064013212002020092200399977699908012020080032202801432030920729518020110099100100800001000001001201115118116020036800001002015420040201552004020040
8020420039166010007588074618010810080008100800205006401320200202009220039997769990801202008003220080032200392003911802011009910010080000100220024301115118016020036800001002004020040200402004020040
80204200391500000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000301115118016020036800001002004020040200402004020040
802042003915000000120030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000010001115118016020036800001002004020040200402004020145
80204200391560100000095258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000010301115118016020077800001002004020040200962004020040
8020420039150000002640030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100200000301115118016020036800001002004020040200402004020040
80204200391500000012001088258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000010301115118116020036800001002004020040200402004020040
802042003915500000120051258010810080112100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000301115119016020036800001002004020040200402004020040
8020420039150010001200469258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000010001115118039020036800001002004020040200402004020040
80204200391600000012001284258010810080008100800205006401320200202003920039997769990801202008003220080032200392003921802011009910010080000100000010601115118016020036800001002004020091200402009420093

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)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)9fa8accfd2d5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511550040258001010800001080000506400001200202003920039999603100198001020800002080000200392003911800211091010800001000502001161120036080000102004020040200402004020040
80024200391553040258001010800001080000506400001200202003920039999603100198001020800002080000200392003911800211091010800001010502001161120036080000102004020040200402004020040
80024200391550040258001010800001080000506400001200202003920039999603100198001020800002080000200392003911800211091010800001000502001161120036080000102004020040200402004020040
8002420039156004025800101080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000100455020101161120036080000102004020040200402004020040
80024200391550040258001010800001080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001000502001161120036080000102004020040200402004020040
80024200391550040258001010800001080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001000502001161120036080000102004020040200402004020040
80024200391550040258001010800001080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001000502001161120036080000102004020040200402004020040
80024200391550040258001010800001080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001000502001161120036080000102004020040200402004020040
80024200391550163258001010800001080000506400001200202003920039999603100198001020800002080000200392003911800211091010800001000502001161120036080000102004020040200402004020040
800242003915600196258001010800001080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001000502001161120036080000102004020040200402004020040