Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTN (scalar, H)

Test 1: uops

Code:

  frintn 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)03070e1e3f4e51inst 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
10043037230006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372300031025472510001000100039816003018303730372414328951000100010003037303711100110001373116112629100030383038303830383038
10043037240006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372700010725472510001000100039816003018303730372414328951000100010003037303711100110000075116112629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723001210325472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
10043037230006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724001716125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintn 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)03070a1e3f4e51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300014329547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000000710216222963300100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000000710216222963300100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000000710216222963300100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000000710216222963300100001003003830038300383003830038
102043003723200081829547251012910010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010006000710216222963300100001003003830038300383003830038
10204300372320006129547251010010010000100100005004277160030018030037300372826532874510100200100002001000030037300371110201100991001001000010000000710216222963300100001003003830038300383003830038
10204301322330006129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000000710216222963300100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010003000710216222963300100001003003830038300383003830038
102043003723300126129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000000710216222963300100001003003830038300843013730038
10204300372410006129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000000710216222963300100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e3f4e51inst 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
100243003724100850295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640416442962910000103003830038300383003830038
10024300372330061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640416342962910000103003830038300383003830038
10024300372320061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640316342962910000103003830038300383003830038
100243003722400837295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640416442962910000103003830038300383003830038
100243003722500726295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640416442962910000103003830038300383003830038
100243003722500181295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640316342962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640416432962910000103003830038300843003830038
10024300372250061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640416442962910000103003830038300383003830038
1002430037240012149295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640316342962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640416442962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)030b181e1f3f51inst 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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006115500003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151182160020036800001002004020040200402004020040
802042003915500005125801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
802042003915500003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
802042003915500003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
802042003915500003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
802042003915600003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
802042003915600003025801081008000810080020500640132020020200392003999776999080228200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
802042003915500005125801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
802042003915500003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039155000886465801161008001610080028500640196020029200482004999769998680128200800382008003820048200481180201100991001008000010003222251281231120045800001002004920050200502005020049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3f51inst 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)9fa0a7a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391550040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050209616532003680000102004020040200402004020040
800242003915500105258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050200516352003680000102004020040200402004020040
800242003915500420258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050200316352003680000102004020040200402004020040
80024200391550063258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050200516552003680000102004020040200402004020040
800242003915500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100001850203516532003680000102004020040200402004020040
800242003916101240258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050223316552003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050200316652003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050200316532003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050200516352003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020800002003920086118002110910108000010000050200547532003680000102004020040200402004020040