Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSUB (scalar, S)

Test 1: uops

Code:

  uqsub s0, s0, s1
  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
100430372208425482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723028925482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723010525482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  uqsub s0, s0, s1
  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)0309181e3f4e51inst 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225004261295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020410000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225000126295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000371011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250215061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225000726295482510100100100001001000050042773131300183003730037282653287451010020010000200200003008430037111020110099100100100001002221671011611296340100001003003830038300383003830038
1020430037225000726295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b18191e3f4e51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000006406162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372240000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103008130038300383003830038
10024300372250000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uqsub s0, s1, s0
  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)03070a18191e1f3f4e51inst 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
102043003722500006012429548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007103162229634100001003003830038300383003830038
10204300372250000906129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100107102162229634100001003003830038300853008630134
102043003722500011718810329548251010011110000104102255004281384030018300373003728265328745101002001000020020000300373003711102011009910010010000100037102162229634100001003003830038300383003830038
1020430037225000000726295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001008067102162229634100001003003830038300383003830038
1020430037225000012061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001002337102162229634100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731303001830037300372826572876310100200100002002000030037300371110201100991001001000010001747102162229634100001003003830038300383003830038
102043003722400000016629548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100067102162229634100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000127102162229634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100037102162229634100001003003830038300383003830038
1020430037225100000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010001087102162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080a181e3a3f4e51inst 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
1002430037224101002682954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010006445165102963010000103003830038300383003830038
10024300372251010026829548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100064411168112963010000103003830038300383003830038
100243003722510110268295482510010101000010100005042773130300183003730081282873287671001020100002020000300373003711100211091010100001000644101612122963010000103003830038300383003830038
10024300372251010026829548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100064451610122963010000103003830038300383003830038
100243003722410100268295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000644101611102963010000103003830038300383003830038
100243003722510100268295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000644101610102963010000103003830038300383003830038
10024300372241010026829548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100064411161062963010000103003830038300383003830038
10024300372251010026829548251001010100001010000504277313130018300373008428287328767100102010000202000030037300371110021109101010000100064451610102963010000103003830038300383003830038
100243003722410100268295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000644101612122963010000103003830038300383003830038
100243003722510100268295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000644111610102963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uqsub s0, s8, s9
  uqsub s1, s8, s9
  uqsub s2, s8, s9
  uqsub s3, s8, s9
  uqsub s4, s8, s9
  uqsub s5, s8, s9
  uqsub s6, s8, s9
  uqsub s7, s8, s9
  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)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)9fa1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003915000000181763025801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001000044060111511801600200360800001002004020040200402004020040
80204200391500000000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100004301350000511011611200360800001002004020040200402004020040
802042003915000000001042580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000000000511011611200360800001002004020040200402004020040
80204200391500000000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100001000000511011611200360800001002004020040200402004020040
802042003915000000004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000750000511011611200360800001002004020040200402004020040
80204200391500000000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000000000511011611200360800001002004020040200402004020040
80204200391500000000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000000000511011611200360800001002004020040200402004020040
80204200391500000000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000000000511011611200360800001002004020040200402004020040
802042003915000000009882580100100800001008000050064000012002020039200399973399978010020080105200160000200392003911802011009910010080000100000000000511011611200360800001002004020040200402004020040
802042003915000000008922580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000000000511011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3f51inst 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)5f60696d6edispatch 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)9fa0a6a8a9accfd0d5d6daddinst fetch restart (de)dfe0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500000402580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001000002750243216022320036080000102004020040200402004020040
8002420039150000040258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000100000350243316032320036080000102004020040200402004020040
8002420039150000040258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000100000350243216042320036080000102004020040200402004020040
8002420039150000040258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000100000350243416044320036080000102004020040200402004020040
8002420039150000040258001010800001080000506400001120020200392003999963100198001020800002016000020039200391180021109101080000100000050243316023320036080000102004020040200402004020040
8002420039150000040438001010800001080000506400001120020200392003999963100198001020800002016000020039200391180021109101080000100000050243216042320036080000102004020040200402004020091
8002420039150001217640258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000100000050243216022320078080000102004020040200402004020040
8002420039150000040258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000100000050243316032320036080000102004020040200402004020040
8002420039150000040258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000100000350243416022320036080000102004020040200402004020040
8002420039150000040258001010800001080000506400001120020200392003999963100198001020800002016000020039200391180021109101080000100000050243316022320036080000102004020040200402004020040