Apple M1 Microarchitecture Research by Dougall Johnson

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

SABD (vector, 2S)

Test 1: uops

Code:

  sabd v0.2s, v0.2s, v1.2s
  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)030b1e3f4e51inst 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
100430372202165325482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723096125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230156125482510001000100039831303018303730372415328951000100020003037303711100110001073116112630100030383038303830383038
10043037230010325482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723106125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230126125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sabd v0.2s, v0.2s, v1.2s
  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)03081e3f4e51inst 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)696b6d6edispatch 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037224006129548251010010010000100100005004277313300180300373003728265032874510100200100002002000030037300371110201100991001001000010047007102161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018030037300842826903287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018030037300372826503287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018030037300372826503287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018030037300372826503287451010020010000200200003003730037111020110099100100100001006007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018030037300372826503287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018030037300372826503287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018030037300372826503287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018030037300372826503287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018030037300372826503287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

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)9fa6cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038
10024300372255586129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038
1002430037225094329548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sabd v0.2s, v1.2s, v0.2s
  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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372251620103295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225504061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372246061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722539061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722518061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372246094295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722518061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372256061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722518061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372251217661295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0309181e1f3f4e51inst 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)dfe0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225003006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300372110021109101010000100064241622229630010000103003830038300383003830038
1002430037225002406129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100064221622229630010000103003830038300383003830038
1002430037225002706129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100064221622229630010000103003830038300383003830038
1002430037225004806129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100064221622229630010000103003830038300383003830038
1002430037225000038729548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100064221622229630010000103003830038300383003830038
10024300372250027306129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300851110021109101010000104064221622229630010000103003830038300383003830038
100243003722500306129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100064221622229630010000103003830038300383003830038
100243003722500606129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100064221622229630010000103003830038300383003830038
100243003722500306129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100064221622229630010000103003830038300383003830038
100243003722500606129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100064221622229630010000103003830038300383008330038

Test 4: throughput

Count: 8

Code:

  sabd v0.2s, v8.2s, v9.2s
  sabd v1.2s, v8.2s, v9.2s
  sabd v2.2s, v8.2s, v9.2s
  sabd v3.2s, v8.2s, v9.2s
  sabd v4.2s, v8.2s, v9.2s
  sabd v5.2s, v8.2s, v9.2s
  sabd v6.2s, v8.2s, v9.2s
  sabd v7.2s, v8.2s, v9.2s
  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)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)9fa6a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815094125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051102161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001002151101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915064125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150124125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802052003915004125801001008000010080000500640000020020200392003999733999780100200800002001600002008820039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150844162802081008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150124125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402009020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03090a181e1f3f51inst 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)9fa0a8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500106040258001010800001080000506400003020020200392003999963100198001020800002016000020039200391180021109101080000100000502013161212200360080000102004020040200402004020040
80024200391500000040258001010800001080000506400007120020200392003999963100198001020800002016000020039200391180021109101080000100000502012161313200360080000102004020040200402004020040
800242003915000118040258001010800001080000506400006020020200392003999963100198001020800002016000020039200391180021109101080000100000502012161112200362180000102004020040200402004020040
80024200391500000040258001010800001080000506400008020020200392003999963100198001020800002016000020039200391180021109101080000100000502013161312200360080000102004020040200402004020040
80024200391500000040258001010800001080000506400007020020200392003999963100198001020800002016000020039200391180021109101080000100000502011161013200360080000102004020090200402004020040
80024200391500000040258001010800001080000506400007120020200392003999963100198001020800002016000020039200391180021109101080000100000502011161112200360080000102004020040200402004020040
80024200391500000040258001010800001080000506400008120020200392003999963100198001020800002016000020039200391180021109101080000100000502013161212200360080000102004020040200402004020040
80024200391500000040258001010800001080000506400007120020200392003999963100198001020800002016000020039200391180021109101080000100000502012161111200360080000102004020040200402004020040
80024200391500000040258001010800001080000506400008120020200392003999963100198001020800002016000020039200391180021109101080000100000502012161112200360080000102004020040200402004020040
80024200391500000040258001010800001080000506400007020020200392003999963100198001020800002016000020039200391180021109101080000100000502011161211200360080000102004020040200402004020040