Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTNU (vector, 4H)

Test 1: uops

Code:

  fcvtnu v0.4h, v0.4h
  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)0304181e1f3a3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372400132028325472510001000100039816030183037303724143289510001000100030373037111001100000377516442629100030383038303830383086
1004303724100026225472510001000100039816030183037303724143289510001000100030373037111001100000077416442695100030383038303830383038
1004303723100026225472510001000100039816030183037303724143289510001000100030373037111001100001077416442629100030383038303830383038
1004303724103026225472510001000100039816030183037303724143289510001000100030373037111001100001077416442629100030383038303830383038
10043037241042028325472510001000100039816030183121303724143289510001000100030373037111001100000077416442629100030383038303830383038
1004303724103026225472510001000100039816030183037303724143289510001000100030373037111001100000377416442629100030383038303830383038
100430372410195026225472510001000100039816030183037303724143289510001000100030373037111001100000077416442629100030383038303830383038
1004303723103026225472510001000100039816030183037303724143289510001000100030373037111001100000077416442629100030383038303830383038
10043037231000210425472510001000100039816030183037303724143289510001000100030373037111001100000077416442629100030383038303830383038
1004303723109028325472510001000100039816030183037303724143289510001000100030373037111001100005077416442629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtnu v0.4h, v0.4h
  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)0318191e3f4e51inst 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)9fa8cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372320006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
10204300372322006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100074111611296330100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
10204300372320006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100171011611296330100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
10204300372320006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
10204300372320006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
10204300372320006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e3f4e51inst 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
1002430037224001861295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640416552962910000103003830038300383003830038
100243003722500061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000661516562962910000103003830038300383003830038
100243003722500061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640616662962910000103003830038300383003830038
100243003722500061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640516552962910000103003830038300383003830038
100243003722500061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001003640616662962910000103003830038300383003830038
1002430037225001861295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640516552962910000103003830086300863003830038
1002430120225406145295382510020101000011100007142771601300183003730037282863287671001020100002010000300373003711100211091010100001000640516652962910000103003830038300383003830038
100243003722500061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001033640516552962910000103003830038300383003830038
100243003722500061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001010640616662962910000103003830038300383003830038
100243003722500082295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000730516662962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtnu v0.4h, v8.4h
  fcvtnu v1.4h, v8.4h
  fcvtnu v2.4h, v8.4h
  fcvtnu v3.4h, v8.4h
  fcvtnu v4.4h, v8.4h
  fcvtnu v5.4h, v8.4h
  fcvtnu v6.4h, v8.4h
  fcvtnu v7.4h, v8.4h
  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)0318191e1f3a3f51inst 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)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058156003000512580108100800081008002050064013212002002003920039997769990801202008003220080032200392003911802011009910010080000100201145118223120036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013202002002003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013212002002003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915500000726080310100800081008002050064013212002002003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915600000302580108100800081008002050064013202002002003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013212002002003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013212002002003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915600300302580108100800081008002050064013212002002003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915600000302580108100800081008002050064013212002002003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
8020420039156000006952580108100800081008002050064013212002002003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03071e3f51inst 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)5f60696b6d6edispatch stall (70)72scheduler 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)9fa8cfd5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501550040258001010800001080000506400000120020320039200399996031001980010208000020800002003920039118002110910108000010050203162220036080000102004020040200402004020040
800242003915501240258001010800001080000506400000120020020039200399996031001980010208000020800002003920039118002110910108000010050202162220036080000102004020040200402004020040
80024200391550040258001010800001080000506400000120020020039200399996031001980010208000020800002003920039118002110910108000010050202162220036080000102004020040200402004020040
80024200391550040258001010800001080000506400000120020020039200399996031001980010208000020800002003920039118002110910108000010050202162220036080000102004020040200402004020040
80024200391550040258001010800001080000506400000120020020039200399996031001980010208000020800002003920039118002110910108000010150202162220036080000102004020040200402004020040
80024200391550040258001010800001080000506400000120020020039200399996031001980010208000020800002003920039118002110910108000010050202162220036080000102004020040200402004020040
80024200391550040258001010800001080000506400000120020020039200399996031001980010208000020800002003920039118002110910108000010050202162220036080000102004020040200402004020040
800242003915503961258001010800001080000506400000120020020039200399996031001980010208010520800002003920039118002110910108000010050202162220036080000102004020040200402004020040
80024200391550040258001010800001080000506400000120020020039200399996031001980010208000020800002003920039118002110910108000010050202162220036080000102004020040200402004020040
80024200391550082258001010800001080000506400000120020020039200399996031001980010208000020800002003920039118002110910108000010050202162220036080000102004020040200402004020040