Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSUB (vector, 16B)

Test 1: uops

Code:

  uqsub v0.16b, v0.16b, v1.16b
  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)03081e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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
100430372200612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831330183037303724153289510001000200030373037111001100002473116112630100030383038303830383038
100430372200612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372300612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230126125482510001000100039831330183037303724153289510001000200030373037111001100043073116112630100030383038303830383038
100430372300612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038308430383038
1004303722006125482510001000100039831330183037303724153289510001000200030373037111001100001273116112630100030383038303830383038
100430372300612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303722008425482510001000100039831330183037303724153289510001000200030373037111001100011073116112630100030383038303830383038
100430372200612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  uqsub v0.16b, v0.16b, v1.16b
  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)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)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)9fa8acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372251026129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225366129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225216129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225216129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722536129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010010007101161129634100001003003830038300383003830038
10204300372253910329548251010010010000104100005004277313030018300373003728269032874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265032874510100204100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037224456129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa0a1a6a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000042900612954825100101010000101000050427731313001830037300372828732876710459201000020200003003730037111002110910101000010000000006402162229630010000103003830181300383003830038
10024300372250000025200612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000041700612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000031500612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500000345001892954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010200000006402162229630010000103003830038300383003830038
10024300372250000035400612954825100411010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383013230038
10024300372250000030900612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000306006402162229630010000103003830038300383003830038
1002430037225000003300612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037211002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000011795280451429485159100711210048121104376428681213029730368304142831535289091105820109862422284301773046410110021109101010000100401419568007444804229882410000103037230369303693036930368
10024304072270118711044400482929485851001010100001010000504277313130018300373008528287328767100102010000202000030037300371110021109101010000102221019513007953723229728510000103037130275304143037130416

Test 3: Latency 1->3

Code:

  uqsub v0.16b, v1.16b, v0.16b
  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)03181e3f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830080
1020430037225012612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500822954825101001001000810010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010010071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038

1000 unrolls and 10 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372241206129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640316222963010000103003830038300383003830038
10024300372253606129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037224423886129476139100722310032141134198428952603034230501303702832643289371135420114742422618304653036911110021109101010000100000640216222963010000103003830038300383003830038
1002430037225906129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830083
10024300372251806129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103007930038300383003830038
100243003722528206129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372256906129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100040640216222963010000103003830038300383003830038
1002430037225606129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uqsub v0.16b, v8.16b, v9.16b
  uqsub v1.16b, v8.16b, v9.16b
  uqsub v2.16b, v8.16b, v9.16b
  uqsub v3.16b, v8.16b, v9.16b
  uqsub v4.16b, v8.16b, v9.16b
  uqsub v5.16b, v8.16b, v9.16b
  uqsub v6.16b, v8.16b, v9.16b
  uqsub v7.16b, v8.16b, v9.16b
  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)030718191e1f3f51inst 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
80204200601500006004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051104163320036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051105165420036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001001051104164320036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051104165520036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051105165420036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000120020201942003999733999780100200800002001600002003920039118020110099100100800001000051104164420036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051105165520036800001002004020040200402004020040
802042003915500015045325801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051104164320036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051103164520036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051105165520036800001002004020040200402004020040

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)~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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150394025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100502010161082003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100502013167102003680000102004020040200402004020040
80024200391502140258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001005020121612122003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100502081611122003680000102004020040200402004020040
800242003915002302580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010050207161072003680000102004020040200402004020040
80024200391500402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010050208168102003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001005020101611122003680000102004020040200402004020040
8002420039149940258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001005020111611122003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001005020101610102003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020202442003999963100198001020800002016000020039200391180021109101080000100502012168122003680000102004020040200402004020040