Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTZS (vector, fixed-point, 4H)

Test 1: uops

Code:

  fcvtzs v0.4h, v0.4h, #3
  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)030809181e1f3f4e51inst 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
10043037240000061254725100010001000398160030183037303724143289510001000100030373037111001100000073116212629100030383038303830383038
10043037240000061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372400057061254725100010001000398160030183037303724143289510001000100030373037111001100000073216112629100030383038303830383038
10043037230000061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303725000132061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037240000061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230000061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300000103254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037240000061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300033061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzs v0.4h, v0.4h, #3
  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)030b1e1f3f4e51inst 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)9fa0a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372320003462954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000006071011611296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000100071011611296600100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000300071011611296330100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010002500071011611296690100001003003830038300383003830038
1020430037232000612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003723400089295372510100100100001001030050042771601300180300373003728264152874510100200100002041000030037300371110201100991001001000010005609071011611296690100001003003830038300383003830038
10204300372330120612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037232000612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000006071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)033f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372326129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100206405166429629010000103003830038300383003830038
1002430037233346295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000276425166629631010000103003830038300383003830038
10024300372336129538251001212100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100206406166529629010000103003830038300383008530038
100243003723261295472510010101000010100005042771600300183003730037282863287671001220100002010000300373003711100211091010100001002306405166629629010000103003830038300383003830038
100243003723261295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001001866406165529629010000103003830038300383003830038
100243003723361295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001002806406166529629010000103003830038300383003830038
100243003723361295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001002766405166629629010000103003830038300383003830038
10024300372416129547251001010100001010000504277160030018300373003728286328767100122010000201000030037300371110021109101010000100706406166629631010000103003830038300383003830038
10024300372336129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100706406166629629010000103003830038300383003830038
100243003723261295472510010101000010100005042771600300183003730037282863287671001220100002010000300373003711100211091010100001001866405166629629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzs v0.4h, v8.4h, #3
  fcvtzs v1.4h, v8.4h, #3
  fcvtzs v2.4h, v8.4h, #3
  fcvtzs v3.4h, v8.4h, #3
  fcvtzs v4.4h, v8.4h, #3
  fcvtzs v5.4h, v8.4h, #3
  fcvtzs v6.4h, v8.4h, #3
  fcvtzs v7.4h, v8.4h, #3
  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)03081e3a3f51inst 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)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)9facc5branch mispredict (cb)cdcfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000251325801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000111512281608820036800001002004020040200402024520040
80204200391500029825801081008000810080020500640132120020200392003999770699908012020080032200800322017320039118020110099100100800001000111512291608920036800001002004020040200402004020040
80204200391500023525801081008000810080020500640132120020200392003999770699908012020280032200800322003920039118020110099100100800001000111512281608920036800001002004020040200402004020040
80204200391500023525801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000111512231609920036800001002004020040200402004020040
80204200391500023525801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000111512291604920036800001002004020040200402004020040
802042003915000235258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010001115122916091020036800001002004020040200402004020040
80204200391490026625801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000111512281608820036800001002004020040200402004020040
80204200391500023525801081008000810080020560640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000111512231603820036800001002004020040200402004020040
80204200391500023525801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000111512281608820036800001002004020040200402004020040
80204200391500025825801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000111512281608820036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b18191e1f3a3f51inst 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)9fa0a1a6a8acc2cfd5d6dbddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015500000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000100502031613320036080000102004020040200402004020040
800242003915500000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000200502011601120036080000102004020040200402004020040
800242003915500000040258001010800001080000506400001200202003920039999631001980032208000020800002003920039118002110910108000010000000502021601120036080000102004020040200402004020040
800242003915500000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000502011601120036080000102004020040200402004020040
800242003915500000140258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000502011601120036080000102004020040200402004020040
8002420039155000120040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000502011602220036080000102004020040200402004020040
800242003915500000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000030502021601120036080000102004020040200402004020040
800242003915500000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000000502011601120036080000102004020040200402004020040
800242003915500000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000502011601120036080000102004020040200402004020040
800242003915600000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000502011602120036080000102004020040200402004020040