Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSUB (vector, 8B)

Test 1: uops

Code:

  sqsub v0.8b, v0.8b, v1.8b
  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)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
1004303722015725482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110002073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110003973116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqsub v0.8b, v0.8b, v1.8b
  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)03090b191e3f4e51inst 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)9fa8acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500090612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372240000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722500012612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722500015612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372330000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000071012611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722500012612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003721102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038

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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500004800612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000306402162229630010000103003830038300383003830038
10024300372250000300384129548451001913100081110298554278670130054302263013128293112879410160201032220206663013330120211002110910101000010200010302546603334329668210000103008530086300853008530085
1002430084225112228817607172952863100191510008101029860428002713005430085301322829032876710010201000020200003003730037111002110910101000010000010306402162229630010000103003830038300383003830038
10024300372240000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500002700612954825100101010000101000050427731313001830037300372828732882310010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000900612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000180058072954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500001800612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500002100612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830085
100243008422600000006129548251001010100001010000504277313130018300373003728287222876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqsub v0.8b, v1.8b, v0.8b
  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)03080b191e1f3f4e51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000720612954825101001001000010010000500427731313001830037300372826532874510100200100002002133230037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225004007262954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000010071015011296340100001003003830038301333003830038
1020430037225000002512954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300375110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250001507262954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000072629548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100020000710116112963428100001003003830038300383003830038
1020430037224000007262954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000030071011611296340100001003003830038300383003830038
10204300372240002407472954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722400000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225000630612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)6061696d6edispatch 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)9fa8a9acc2branch mispredict (cb)cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000024061295482510010101000010100005042773131030018300373003728287328767100102010000202000030037300371110021109101010000100000064000416332963010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773130030018300373003728287328767100102010000202000030037300371110021109101010000100000064000416342963010000103003830038300383003830038
10024300372250000027061295482510010101000010100005042773130030018300373003728287328767100102010000202000030037300371110021109101010000100000064000316342963010000103003830038300383003830038
1002430037224000000061295482510010101000010100005042773131030018300373003728287328767100102010000202000030037300371110021109101010000100000064000416342963010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773130030018300373003728287328767100102010000202000030037300371110021109101010000100000064000416342963010000103003830038300383003830038
100243003722500000120726295482510010101000010100005042773130030018300373003728287328767100102010000202000030037300371110021109101010000100000064000316442963010000103003830038300383003830038
10024300372250000030536295482510010101000010100005042773130030018300373003728291328767100102010000202000030037300371110021109101010000100000064000316342963010000103003830038300383003830038
10024300372250000024061295482510010101000010100005042777991030018300373003728287328767101592010000202000030037300371110021109101010000100000064000316432963010000103003830038300383003830038
10024300372250000030061295482510010101000010100005042773131030018300373003728287328767100102010000202000030037300371110021109101010000100000064000316342963010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773130030018300373003728287328767100102010000202000030037300371110021109101010000100000064000316442963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqsub v0.8b, v8.8b, v9.8b
  sqsub v1.8b, v8.8b, v9.8b
  sqsub v2.8b, v8.8b, v9.8b
  sqsub v3.8b, v8.8b, v9.8b
  sqsub v4.8b, v8.8b, v9.8b
  sqsub v5.8b, v8.8b, v9.8b
  sqsub v6.8b, v8.8b, v9.8b
  sqsub v7.8b, v8.8b, v9.8b
  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)03081e3f5051inst 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
802042004815101541025801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051103163320036800001002004020040200402004020040
80204200391500041025801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051103163320036800001002004020040200402004020040
802042003915002741025801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051103172320036800001002004020040200402004020040
80204200391500041025801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051103163220036800001002004020040200402004020040
80204200391500641025801001008000010080000500640000120020200392003999733999780100200804172001600002003920039118020110099100100800001000051103163220036800001002004020040200402004020040
80204200391500041025801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051102162320036800001002004020040200402004020040
80204200391500341025801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051103162320036800001002004020040200402004020040
80204200391500341025801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051103163320036800001002004020040200402004020040
802042003915002141025801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051102164320036800001002004020040200402004020040
80204200391500041025801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051103163320036800001002004020040200402004020040

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)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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150040258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010005020011165112003680000102004020040200402004020040
800242003915034025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000502001116542003680000102004020040200402004020040
800242003915015402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100350200516442003680000102004020040200402004020040
80024200391509402580010108000010800005064000020020200392003999963101278001020800002016000020039200391180021109101080000100050200716542003680000102004020040200402004020040
80024200981500402580010108000012800005064000020020200392003999963100198001020800002016000020039200391180021109101080000103350200416552003680000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200616652003680000102004020040200402004020040
800242003915094025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000502006165112003680000102004020040200402004020040
8002420039150124025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000502005165112003680000102004020040200402004020040
80024200391509402580010108000010800005064000020020200392003999963101278001020800002016000020039200391180021109101080000100050200516552003680000102004020040200402004020040
80024200391509402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200516392003680000102004020040200402004020040