Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTA (scalar, H)

Test 1: uops

Code:

  frinta h0, h0
  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)0308181e3f4e51inst 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)a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100020200073216222629100030383038303830383038
100430372300361254725100010001000398160130183037303724143289510001000100030373037111001100000000073216222645100030383038303830383038
100430372200061254725100010001000398160030183037303724143289510001000100030373037111001100000000073216222629100030383038303830383038
100430372200061254725100010001000398160030183037303724143289510001000100030373037111001100000000073216222629100030383038303830383038
100430372300061254725100010001000398160130183037303724143289510001000100030373037111001100000003073216222629100030383038303830383038
100430372300061254725100010001000398160130183037303724143289510001000100030373037111001100000000073216222629100030383038303830383038
100430372300061254725100010001000398160130183037303724143289510001000100030373037111001100000000073216222629100030383038303830383038
100430372300061254725100010001000398160130183037303724143289510001000100030373037111001100000000073216222629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100000000073216222629100030383038303830383038
1004303723000612547251008100010003981600301830373037241432895100010001000303730371110011000021743473216222629100030383085303830383122

Test 2: Latency 1->2

Code:

  frinta h0, h0
  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)03090b191e1f3f4e51inst 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)9fa0a6a8a9acc2branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330003061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
1020430037233000120726295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
102043003723300012061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000300071011611296330100001003003830038300383003830038
10204300372320000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
10204300372330000061295479710100100100001001000066242771601300183003730037282773287451010020010000216100003003730037111020110099100100100001000000000071011613296330100001003003830038300383003830038
1020430037233010001346295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071011631296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0304080b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cacdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372410000027029129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000030006402162229629010000103003830038300383003830038
1002430037233000000029829547251001010100001010000504277160030018301313003728286328767100102010000201000030037300371110021109101010000100001000006402162229629010000103003830038301323008630038
1002430178234010030085329547251001010100001010000504277160030090302253013228286328840104642010000201000030037300371110021109101010000100000090006402162229629010000103022530086301813003830133
1002430037233010000088629547251001010100001010000504277160030090300733003728286828805100102010000201016230037300371110021109101010000100020000006402162229629010000103003830038300383003830038
1002430037233000000021029547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110022109101010000100000000006402162229629010000103003830038300383003830038
1002430037233000000014929547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000017063622429775110000103013430227300853003830224
1002430228233001040136270729511100100261010032111060050427716013016230037302252829821288441061522100002010329302253022851100211091010100001006202111300006402162229629010000103074930312300863003830133
10024302262410000000789295472510010101000010100006642771601300183003730037282863287671001020100002010000300373003711100211091010100001000000334800006402162229629010000103003830038300383003830038
1002430083233000000016729493251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
10024300372320000000226295472510010101000010100005042771600300183003730037282863287671001024121313011316306463049715110021109101010000100000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frinta h0, h8
  frinta h1, h8
  frinta h2, h8
  frinta h3, h8
  frinta h4, h8
  frinta h5, h8
  frinta h6, h8
  frinta h7, h8
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)030b18191e1f3f51inst 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)9fa1a7a8a9acc2c5branch mispredict (cb)cdcfd5d6dcddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500000030258010810080008123800205006401322002020039200399977699908012020280032200800322003920096118020110099100100800001000000001115118016010200360800001002004020040200402004020040
80204200391501000030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016110200360800001002004020040200402004020040
80204200391500000030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001002010301115137028000200360800001002004020040200402004020040
802042009015000112030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016000200360800001002004020040200402004020040
802042003915000039072258010810080008100800205006401322002020039200399977699908012020080032200800322003920039218020110099100100800001000000001115118016000200360800001002004020040200402004020040
80204200391500000030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016000200360800001002004020040200402004020040
802042003915000012030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016000200360800001002004020040200402004020040
802042003915000014726458258010810080008100800205006401322002020039200899977699908012020080032200800322003920039118020110099100100800001000000301115118016000200360800001002004020040200402004020040
80204200391490000030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016000200360800001002004020040200402004020040
80204200391500000030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016010200360800001002004020040200402004020040

1000 unrolls and 10 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)9fa1a6a7a8acc2cficache miss (d3)itlb miss (d4)d5d6ddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391550000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000502000131633200360080000102004020040200402004020040
80024200391560001204025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050200061644200360080000102004020040200402004020040
8002420039155000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050200061644200360080000102004020040200402004020040
80024200391610001804025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050200071633200360080000102004020040200402004020040
8002420039155000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050200051645200360080000102004020040200402004020040
8002420039155000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050200041644200360080000102004020040200402004020040
80025200391550000010325800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050200061644200360080000102004020040200402004020040
8002420039156000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050200061633200360080000102004020040200402004020040
8002420039155000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050200041643200360080000102004020040200402004020040
8002420039155000008225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050200041654200360080000102004020040200402004020040