Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTP (scalar, H)

Test 1: uops

Code:

  frintp 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)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)a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723361254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723082254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230103254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintp 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)03080b18191e1f3f4e51inst 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)9fa1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000003071011611296330100001003003830038300383003830038
102043003723300000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372330000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000123071011611296330100001003003830038300383003830038
102043003723300000061295472510100100100001001000050042771600300183003730037282923287451010020010000200100003003730037111020110099100100100001000003071011611296330100001003003830038300383003830038
1020430037233000012061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000003071011611296330100001003003830038300383003830038
102043003723300000061295472510100100100001001060050042771601300543003730037282643287451010020010000200100003003730037111020110099100100100001000003071011611296330100001003003830038300383003830038
1020430037233000000276295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000003071011611296330100001003003830038300383003830038
102043003723300000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000006071011611296330100001003003830038300383003830038
1020430037232000000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000051071011611296330100001003003830038300383003830038
102043003723200000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000006071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst 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)6061696b6d6edispatch 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)9fa8a9acc2cfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500612954725100101010000101000050427716010300180300373003728286328767100102010000201000030037300371110021109101010000100000640002162229629010000103003830038301793003830038
1002430037225005362954725100101010000101000050427716010300183300373003728286328767100102010000201000030037300371110021109101010000100000640002162229629010000103003830038300383003830038
1002430037224001562954725100101010000101000050427716004300180300373003728286328767100102010000201000030037300371110021109101010000100000640002162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716010300180300373003728286328767100102010000201000030037300371110021109101010000100000640002162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716004300180300373003728286328767100102010000201000030037300371110021109101010000100001640002162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716004300180300373003728286328767100102010000201000030037300371110021109101010000100000640002162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716004300180300373003728286328767100102010000201000030037300371110021109101010000100000640442162229629010000103003830038300383003830038
1002430037225006129529441001911100081110300554278512043005403013330131282911128803101612010330201032530131301313110021109101010000100227700684043333329667110000103012130085300863008530086
1002430084226186120207029538251001011100081110300664279864103005403013130084282911028804103122210162201033630085300842110021109101010000101030640442162229629010000103003830038300383003830038
1002430037225001812954725100101010000101000050427716004300180300373003728286328767100102010000201000030037300371110021109101010000100000640442162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintp h0, h8
  frintp h1, h8
  frintp h2, h8
  frintp h3, h8
  frintp h4, h8
  frintp h5, h8
  frintp h6, h8
  frintp 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)031e3a3f5051inst 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)9fa6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042004915502350258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100005411151227168920036800001002004020040200402004020040
80204200391550235025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010001011151228163620036800001002004020040200402004020040
80204200391550235025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010002011151228168820036800001002004020040200402004020040
80204200391560235025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010001611151228168920036800001002004020040200402004020040
802042003915502350258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100042311151228166620036800001002004020040200402004020040
8020420039156022250258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100037611151228163820036800001002004020040200402004020040
80204200391560274025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010001011151229166620036800001002004020040200402004020040
802042003915502350258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100018411151228168820036800001002004020040200402004020040
802042003915502350258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100008711151229168820036800001002004020040200402004020040
802042003915502330025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151226168820036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391550822580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000102005020916222003680000102004020040200402004020040
80024200391550402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000101005020216362003680000102004020040200402004020040
80024200391560402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000103715605020216222003680000102004020040200402004020040
80024200391610402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000104005020616622003680000102004020040200402004020040
800242003915506825800101080000108000050640000020081200392003999963100198001020800002080000200392003911800211091010800001050005020216262003680000102004020040200402004020040
80024200391550402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000102005020216362003680000102004020040200402004020040
80024200391550402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000103605020216222003680000102004020040200402004020040
80024200391550402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000101005020316232003680000102004020040200402004020040
80024200391550402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000101305020316222003680000102004020040200402004020040
800242003915604202580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000103005020616322003680000102004020040200402004020040