Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMULH (vector, 4S)

Test 1: uops

Code:

  sqdmulh v0.4s, v0.4s, v1.4s
  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)031e1f3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723008225482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303722006125482510001000100039831303018303730372415328951000100020003037303711100110000973116112630100030383038303830383038
1004303722006125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230012625482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303722006125482510001000100039831313018303730372415328951000100020003037303711100110001073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100020003037303711100110000073116212630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqdmulh v0.4s, v0.4s, v1.4s
  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)031e1f3f4e51inst 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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250072629548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300843008621102011009910010010000100100071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372269886129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030708090a0b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000480061295482510010101000010100005042773130300183003730037283033287671001020100002020000300373003711100211091010100001000000006403242229630010000103003830038300383003830038
10024300372240000000240061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630210000103003830038300853003830038
10024300372250000000210061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103032230322303243032330371
10024303662283110176939616045822948545100691410056171089487428681203027030367304042831833289161097026109782222290303663037281100211091010100001004012279027883955229902110000103037130405303723037030370
100243041722701001779426160612954825100101010000101000050427731303001830037300372828732880510607201000020200003003730037111002110910101000010402101671007723653429848110000103036830321304193035730370
10024303712270100177107461611367294941591007014100641411043814286812030270303233035828318332889511056201130422222903008430361811002110910101000010023001938026402162229630010000103003830038300383003830038
100243003722500011881101704052672945723510103111008815113416042895260303783050930509283275228975115032411490222361630557305111111002110910101000010020102748808304963430029010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqdmulh v0.4s, v1.4s, v0.4s
  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)0308090b18191e1f3a3f4e51inst 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)9fa0a1a7a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000061295482510100100100001001000050042773131300180300373003728265328745101002001000020020000300373003711102011009910010010000100000001230071011611296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773131300180300373003728265328745101002001000020020000300373003711102011009910010010000100000001260071011611296340100001003003830038300383003830038
102043003722500000000612953925101001001000010010000500427731313001803003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
1020430037225000000007262954825101001001000010010000500427731313001803003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000000125295482510100100100001001000050042773131300180300373003728265328745101002001000020020000300373003711102011009910010010000100000001620071011611296340100001003003830038300383003830038
10204300372250000000072629548251010010010000100100005004277313130018030037300372826532874510100200100002002000030037300371110201100991001001000010000000960071011611296340100001003003830038300383003830038
102043003722500000000251295482510100100100001001000050042773131300180300373003728265328745101002001000020020000300373003711102011009910010010000100000001050071011611296340100001003003830038300383003830038
102043003722500000000251295482510100100100001001000050042773131300180300373003728265328745101002001000020020000300373003711102011009910010010000100000001110071011611296340100001003003830038300383003830038
1020430037224000000005792954825101001001000010010000500427844713001803003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018030037300372826532874510100200100002002000030037300371110201100991001001000010000000840071011611296340100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722502752954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000300640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010002000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010030000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000020640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
10024300372240612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqdmulh v0.4s, v8.4s, v9.4s
  sqdmulh v1.4s, v8.4s, v9.4s
  sqdmulh v2.4s, v8.4s, v9.4s
  sqdmulh v3.4s, v8.4s, v9.4s
  sqdmulh v4.4s, v8.4s, v9.4s
  sqdmulh v5.4s, v8.4s, v9.4s
  sqdmulh v6.4s, v8.4s, v9.4s
  sqdmulh v7.4s, v8.4s, v9.4s
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 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)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)9fa7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015108025801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100000051104164420036800001002004020040200402004020040
8020420039150010425801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100000051104165520036800001002004020040200402004020040
8020420039150012725801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100010051104164420036800001002004020040200402004020040
802042003915006225801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100000051105164520036800001002004020040200402004020040
8020420039150014625801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100010051104163520036800001002004020040200402004020040
8020420039150080525801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100000051104165520036800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100000051104165420036800001002004020040200402004020040
8020420039150010425801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100000051105166520036800001002004020040200402004020040
8020420039150019825801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100000051105165420036800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100000051104164520036800001002004020040200402004020040

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)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)9fa0a7a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000005020616422003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000005020216242003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000010505020216242003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000005020216242003680000102004020040200402004020040
800242003915000402580010108029112800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000905020416542003680000102004020040201992004020040
8002420039150104025800101080000108000050640000120020201932003999963100198001020804172016000020039200391180021109101080000100011205020416462003680000102004020040200402004020040
800242003915002257052580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000005020316452003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010001005020416422003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000005020416422003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000005020416422003680000102004020040200402004020040