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, D)

Test 1: uops

Code:

  frintn d0, d0
  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)03091e3f4e51inst 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
100430372301261254725100010001000398160130183037303724143289510001000100030373037111001100003073116112629100030383038303830383038
10043037240151523254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723014161254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037240061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037240061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230961254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372301261254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037240361254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300168254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintn d0, d0
  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)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)9fa8acc2cfd5d6daddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710116011296330100001003003830038300383003830038
10204300372330612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710116011296330100001003003830038300383003830038
10204300372330612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710116011296330100001003003830038300383003830038
10204300372330892954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100060710116011296720100001003003830038300383003830038
102043003723307262954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710116011296330100001003003830038300383003830038
10204300372320612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710116011296330100001003003830038300383003830038
102043003723306129547251010010010005100100005004277160300183003730037282642528745101002001000020010000300373003711102011009910010010000100000710116011296330100001003003830038300383003830038
10204300372320612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710116011296330100001003003830038300383003830038
10204300372330612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100030710116011296330100001003003830038300383003830038
10204300372330612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710116011296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080f18191e1f3f4e4f51inst 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)9fa8a9acc2cfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250200004892954702510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000006404162229629010000103003830038300383003830038
10024300372250000001872954702510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250000001932954702510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229699010000103003830038300383003830038
10024300372250000001262954702510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
1002430037225000000145295470251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962914310000103003830038300383003830038
1002430037225000000612954702510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
1002430037225000000612954702510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
1002430037225000000612954702510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
1002430037225000000612954702510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
100243003722500009001472954702510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintn d0, d8
  frintn d1, d8
  frintn d2, d8
  frintn d3, d8
  frintn d4, d8
  frintn d5, d8
  frintn d6, d8
  frintn d7, d8
  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)03070a193f51inst 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)9fa0a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815511030258010810080008100800205006401320200200200392003999776999080120200800322008003220048200491180201100991001008000010000011151186161120036800001002004020040200402004020040
802042003915513030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
802042003915513030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
802042003915513030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010010011151181161120036800001002004020040200402004020040
802042003915513030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
802042003916113030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151181171120036800001002004020040200402004020040
802042003915013030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
802042003915013030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
802042003915013030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
8020420039150130180258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)9fa8accfd5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050156004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100050205162232003680000102004020040200402004020040
8002420039156004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050203160332003680000102004020040200402004020040
80024200391550040258010910800001080000506400000020020200392003910005710019800102080000208009920097200391180021109101080000100050204160322003680000102004020040200402008920040
800242003915512764025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050203160322003680000102004020040200402004020040
8002420039155004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050203160242003680000102004020040200402004020040
80024200391550065825800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050204160322003680000102004020040200402004020040
8002420039155004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050203160332003680000102004020040200402004020040
8002420039155004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050203160332003680000102004020040200402004020040
8002420039155004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050202160322003680000102004020040200402004020040
8002420039155004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050203160232003680000102004020040200402004020040