Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTZ (scalar, S)

Test 1: uops

Code:

  frintz 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
1004303723010325472510001000100039816003018303730372414328951000100010003037303711100110000373216222629100030383038303830383038
1004303723010325472510001000100039816003018303730372414328951000100010003037303711100110001373216222629100030383038303830383038
1004303723126125474310001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110001073216222629100030383038303830383038
1004303723126125472510001000100039816003018303730372414328951000100010003037303711100110000373216222629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000373216222629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110001073216222629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110001073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintz 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)031e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100137102162229633100001003003830038300383003830038
10204300372251210329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373008011102011009910010010000100107102162229633100001003003830038300383003830038
10204300372251210329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100037102162229633100001003003830038300383003830038
10204300372251210329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100037102162229633100001003003830038300383003830038
1020430037225010329547251010010010000100100005004277160130018300373003728264328745101002141000020010000300373003711102011009910010010000100137102162229633100001003003830038300383003830038
1020430037225010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100137102162229633100001003003830038300383003830038
10204300372251210329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100137102162229633100001003003830038300383003830038
1020430037225074729529251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100137102162229633100001003003830038300383003830038
1020430037225010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100137102162229633100001003003830038300383003830038
10204300372251210329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100137102162229633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03090a0b18191e1f3f4e51inst 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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000870295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372250000000726295472510010101000010100005042771601300183003730037282863287671016020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372250000018061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372250000000538295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222977310000103003830038300383003830038
1002430037225000400061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000640216232962910000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001004000640216222962910000103003830038300383003830038
10024300372250000000170295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001020000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintz s0, s8
  frintz s1, s8
  frintz s2, s8
  frintz s3, s8
  frintz s4, s8
  frintz s5, s8
  frintz s6, s8
  frintz 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)9fa1a6a8a9acc2c5branch mispredict (cb)cdcfd6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006115000012072258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001030111511816020036800001002004020040200402004020040
8020420039150000120156258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001030111511816020036800001002004020040200402004020040
802042003915000012030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511816020036800001002004020040200912004020040
80204200391500000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001030111511816020036800001002004020040200402004020040
802042003915000012072258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001000111511816020036800001002004020040200402004020040
802042003915000012072258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001030111511816020036800001002004020040200402004020040
802042003915100012072258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000030111511816020036800001002004020040200402004020040
802042003915000012093258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001000111511816020036800001002004020040200402004020040
802042003915000012072258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001030111511816020036800001002004020040200402004020040
802042003915000012072258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001030111511816020036800001002004020040200402004020040

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)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)9fa1a8c5cfd0d2itlb miss (d4)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150034125800101080000108000050640000052002020039200399996310019800102080000208000020039200391180021109101080000102005024001141616162003680000102004020040200402004020040
8002420039150024125800101080000108000050640000152002020039200399996310019800102080000208000020039200391180021109101080000100005024500141617152003680000102004020040200402004020040
8002420039150024125800101080000108000050640000152002020039200399996310019800102080000208000020039200391180021109101080000100005024500131614162003680000102004020040200402004020040
8002420039150024125800101080000108000050640000152002020039200399996310019800102080000208000020039200391180021109101080000100005024500151616162003680000102004020040200402004020040
800242003915002412580010108000010800005064000015200202003920039999631001980010208000020800002003920039118002110910108000010000502450081616142003680000102004020040200402004020040
8002420039150026002580010108000010800005064000015200202003920039999631001980010208000020800002003920039118002110910108000010000502450014169152003680000102004020040200402004020040
8002420039150024125800101080000108000050640000052002020039200399996310019800102080000208000020039200391180021109101080000100005024000151615162003680000102004020040200402004020040
800242003915002412580010108000010800005064000005200202003920039999631001980010208000020800002003920039118002110910108000010000502450020161682003680000102004020040200402004020040
8002420039150024125800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100005024000171614162003680000102004020040200402004020040
80024200391500242125800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100005024500181615162003680000102004020040200402004020040