Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTI (scalar, S)

Test 1: uops

Code:

  frinti 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)031e3f4e51inst 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
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372408225472510001000100039816013018303730372414328951000100010003037303711100110001073216112629100030383038303830383038
1004303724014725472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110001373116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724186125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383086303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frinti 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)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)9fa8cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300012061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000710011611296330100001003003830038300383003830038
102043003723200011117661295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000710011611296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000710011611296330100001003003830038300383003830038
10204300372850000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000710011611296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000710011611296330100001003003830038300383003830038
10204300372320000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000710011611296330100001003003830038300383003830038
102043003723200000726295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000742111611296330100001003003830038300383003830038
102043003723300000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010046710011611296330100001003003830038300383003830038
10204300372410000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000710011611296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000710011611296330100001003003830038300383003830038

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)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)9fa0a6a7a8a9acc2branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000023129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
100243003722400000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
100243003722400000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100001000106402162229629010000103003830038300383003830038
1002430037224000000010529547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
100243003722500100006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037224000000012629547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037225000000010329547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frinti s0, s8
  frinti s1, s8
  frinti s2, s8
  frinti s3, s8
  frinti s4, s8
  frinti s5, s8
  frinti s6, s8
  frinti 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)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)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)9fa0a1a6a7a8a9acafc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611560000000695258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000000111511801600200360800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000000111511801600200360800001002004020040200402004020040
8020420039155000090030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000010000111511801620200360800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000000111511801700200360800001002004020040200402004020040
8020420039161000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000000111511801600200360800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000000111511801600200360800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000000111511801600200360800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000000111511801600200360800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401321200202003920039997769990801202008013820080032200392003911802011009910010080000100000000000111511801600200360800001002004020040200402004020040
8020420039155000000058258021610080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100020004000111511801600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b181e1f3a3f51inst 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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401550000040258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000000000502001161120036080000102004020040200402004020040
80024200391550000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502001161120036080000102004020040200402004020040
80024200391550000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502001161120036080000102004020040200402004020040
800242003915500120040258001010800001080000506400001120020200392003999963100198001020800002080000200392003911800211091010800001000000000502001161120036080000102004020040200402004020040
80024200391550000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502001161120036080000102004020040200402004020040
80024200391550000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001022202001502001161120036080000102004020040200402004020040
80024200391610000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502001161120036080000102004020040200402004020040
80024200391550000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502001161120036080000102004020040200402004020040
800242003915600000325258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502001161120036080000102004020040200402004020040
80024200891560000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502001161120036080000102004020040200402004020040