Apple M1 Microarchitecture Research by Dougall Johnson

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

FMAXV (4H)

Test 1: uops

Code:

  fmaxv h0, 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)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696b6d6edispatch 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230612547251000100010003981601301803037303724143289510001000100030373037111001100000073216112629100030383038303830383038
10043037220612547251000100010003981600301803037303724143289510001000100030373037111001100020073116112629100030383038303830383038
10043037230612547251000100010003981601301803037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372206212547251000100010003981601301803037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037220612547251000100010003981601301803037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230612547251000100010003981601301803037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230612547251000100010003981600301803037303724143289510001000100030373037111001100000373116112629100030383038303830383038
100430372303362547251000100010003981601301803037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230612547251000100010003981600301803037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037220612547251000100010003981600302203037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fmaxv h0, 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)03083f4e51inst 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)9fa1a6a8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037224061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000400071011611296330100001003003830038300383003830038
1020430037238061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000400071011611296330100001003003830038300383003830038
1020430037225161295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000300071011611296330100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000013012071011611296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000100071011611296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037224061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000003071011611296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000100071011611296330100001003003830038300383003830038
1020430037224061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000200071011611296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000300071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa1a6a7a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372320001000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000003006406163329629010000103003830038300383003830038
10024300372250000000822954725100101110000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006403163329629010000103003830038300383003830038
1002430037224000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001003010111006403163329629010000103003830038300383003830038
10024300372251000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000200006403163329629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006403163329629010000103003830038300383003830038
10024300372240000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000409006405163329629010000103003830038300383003830085
100243003722500000004625294841371002018100561211050654285272130126303693032028311828883109142210968221097830355303688110021109101010000100205019499207674723329946310000103037030406303713036930228
1002430369227107792488052672948415310071131004816106006542866241302703021530369283083028889110642411147261122830371303226110021109101010000102214020650007933744429881510000103041430417304193027730419
1002430226228118912007041574429475173100841310024141126375428932803030630462304612829841289191121524113062211316301793051010110021109101010000102201019415406616423429870310000103003830038300383003830038
10024300372250000600612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006403163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fmaxv h0, v8.4h
  fmaxv h1, v8.4h
  fmaxv h2, v8.4h
  fmaxv h3, v8.4h
  fmaxv h4, v8.4h
  fmaxv h5, v8.4h
  fmaxv h6, v8.4h
  fmaxv h7, 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)03080918191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200691500000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
80204200391500000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000100111511801600200360800001002004020040200402004020040
80204200391500000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000200111511801600200360800001002004020040200402004020040
80204200391500000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
80204200391500000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
80204200391500000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000003111511801600200360800001002004020040200402004020040
80204200391500000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
80204200391500000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000005400111511801600200360800001002004020040200402004020040
80204200391500000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000100111511801600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b18191e1f3f51inst 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)9fa0a1a6a8a9accfd5d6daddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150000006040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000502041605520036080000102004020040200402004020040
8002420039150000000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000000502051606520036080000102004020040200402004020040
8002420039150000000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000502051604520036080000102004020040200402004020040
8002420039150000000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000502051607620036080000102004020040200402004020040
8002420039150000000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000103502092904420036080000102004020040200402004020040
8002420039150000000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000502051605520036080000102004020040200402004020040
80024200391500000000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100002509502051605420036080000102004020040200402004020040
80024200391500000000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100003500502061606620036080000102004020040200402004020040
8002420039150000000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000100502051606520036080000102004020040200402004020040
80024200391500000000763258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000103502061605520036080000102004020040200402004020040