Apple M1 Microarchitecture Research by Dougall Johnson

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

MOVI (vector, 4S, msl)

Test 1: uops

Code:

  movi v0.4s, #3, msl #8

(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)031e3f51inst 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)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004288204025100010001000700002692882881233146100010002882881110011000073116112851000289289289289289
1004288204025100010001000700002692882881233146100010002882881110011000073116112851000289289289289289
1004288204025100010001000700002692882881233146100010002882881110011000073116112851000289289289289289
1004288204025100010001000700002692882881233146100010002882881110011000073116112851000289289289289289
1004288204025100010001000700002692882881233146100010002882881110011000173116112851000289289289289289
1004288204025100010001000700002692882881233146100010002882881110011000073116112851000289289289289289
1004288204025100010001000700002692882881233146100010002882881110011000073116112851000289289289289289
1004288204025100010001000700002692882881233146100010002882881110011000073116112851000289289289289289
1004288204025100010001000700002692882881233146100010002882881110011000073116112851000289289289289289
1004288204025100010001000700002692882881233146100010002882881110011000073116112851000289289289289289

Test 2: throughput

Count: 8

Code:

  movi v0.4s, #3, msl #8
  movi v1.4s, #3, msl #8
  movi v2.4s, #3, msl #8
  movi v3.4s, #3, msl #8
  movi v4.4s, #3, msl #8
  movi v5.4s, #3, msl #8
  movi v6.4s, #3, msl #8
  movi v7.4s, #3, msl #8

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03080b18191e1f3f51inst 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)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)9fa0a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815500001140402580100100800001008000050056000012001920038200389973399968010020080000200200382003811802011009910010080000100000000052142982320280230800001002009120352203512035020396
80204202911570027660440117125805851238046512580484608563382020218201982029110024241012880603200804882022029320348618020110099100100800001004000329040516431122220240220800001002045120451204502050020451
80204204511591091010566161813179808741068083812280786626566130020348203362033810032421021080902200808862082039620497918020110099100100800001000012421040525821272120350220800001002043920446205142045620445
802042048115901881065704270118180862121807421088078659956608302033820443204419997391020781110204807802002039620447918020110099100100800001000202374500522631062220321220800001002019020345201402034720347
802042034615811000040258010010080000100800005005600000200192003820038997339996801002008000020020038200381180201100991001008000010000000005110216222003500800001002003920039200392003920039
802042003815500000040258010010080000100800005005600000200192003820038997339996801002008000020020038200381180201100991001008000010000000005110216222003500800001002003920039200392003920039
8020420038155000000325258010010080000100800005005600000200192003820038997339996801002008000020020038200381180201100991001008000010000000005110216222003500800001002003920039200392003920039
802042003815500000040258010010080000100800005005600000200192003820038997339996801002008000020020038200381180201100991001008000010000000005110216222003500800001002003920039200392003920039
802042003815500000040258010010080000100800005005600000200992003820038997339996801002008000020020038200381180201100991001008000010000100005110216222003500800001002003920039200392003920039
802042003815500000040258010010080000100800005005600000200192003820038997339996801002008000020020038200381180201100991001008000010000000005110216222003500800001002003920039200392003920039

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)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)9fa1a6a8accfd2icache miss (d3)d5d6d9ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815512392580010108000010800005056000002001920038200389996310018800102080000202003820038118002110910108000010000050200061604620035080000102003920039200392003920039
800242003815527392580010108000010800005056000012001920038200389996310018800102080000202003820038118002110910108000010000050200021602420035080000102003920039200392003920039
80024200381550392580010108000010800005056000002001920038200389996310018800102080000202003820038118002110910108000010000050200041604220035080000102003920039200392003920039
80024200381560392580010108000010800005056000012001920038200389996310018800102080000202003820038118002110910108000010000050200031604220035080000102003920039200392003920039
80024200381550392580010108000010800005056000002001920038200389996310018800102080000202003820038118002110910108000010000050200021604220035080000102003920039200392003920039
80024200381550392580010108000010800005056000002001920038200389996310018800102080000202003820038118002110910108000010000050200051602420035080000102003920039200392003920039
80024200381550392580010108000010800005056000002001920038200389996310018800102080000202003820038118002110910108000010000050200021602420035080000102003920039200392003920039
80024200381550392580010108000010800005056000002001920038200389996310018800102080000202003820038118002110910108000010000050200061602420035080000102003920039200392003920039
80024200381550392580010108000010800005056000002001920038200389996310018800102080000202003820038118002110910108000010000050200021604220035080000102003920039200392003920039
80024200381560392580010108000010800005056000002001920038200389996310018800102080000202003820038118002110910108000010000050200051602420035080000102003920039200392003920039