Apple M1 Microarchitecture Research by Dougall Johnson

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

ADDHN (vector, 4S)

Test 1: uops

Code:

  addhn v0.4h, 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)03090b18191e1f3f4e51inst 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)a8a9cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230000006125482510001000100039831313018303730372415328951000100020003037303711100110001073216112630100030383038303830383038
10043037230000006125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037220000006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372200000028725482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372300000025125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230000006125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230000008425482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230000006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037220000008225482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230000006125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  addhn v0.4h, 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)03090b18191e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037224000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430084225000066129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430084225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038

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)9fa1a6a8acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630310000103003830038300383003830038
100243003722506129548441001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722406129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006402163329630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300813003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  addhn v0.4h, 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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000094295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250009061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500027061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500012061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500015061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722400015061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500015061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007351161129634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500015061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

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)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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722517161295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225361295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372251561295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372251561295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372252461295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010056150640216222963010000103003830038300383003830038
10024300372251561295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372251261295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372251261295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037224061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010202640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  addhn v0.4h, v8.4s, v9.4s
  addhn v1.4h, v8.4s, v9.4s
  addhn v2.4h, v8.4s, v9.4s
  addhn v3.4h, v8.4s, v9.4s
  addhn v4.4h, v8.4s, v9.4s
  addhn v5.4h, v8.4s, v9.4s
  addhn v6.4h, v8.4s, v9.4s
  addhn v7.4h, 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)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)9fa0cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000511021611200360800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000511011611200360800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000511011611200360800001002004020040200402004020040
802042003915064125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000511011611200360800001002004020040200402004020040
8020420039150051625801001008000010080000500640000120020200392003999823999780100200800002001600002003920039118020110099100100800001000511011611200360800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000511011611200360800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000511011611200360800001002004020040200402004020040
8020420039150041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010005110116112007922800001002004020040200402004020040
802042003915004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000511011611200360800001002004020040200402004020040
80204200391502254125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000511011611200360800001002004020040200402010120040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500082258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050202716152520036180000102004020040200402004020040
80024200391500940258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050202516252520036080000102004020040200402004020040
8002420039150025240258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050202516252420036080000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050202516192520036080000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050202516252620036080000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050202516252520036080000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050202516182520036080000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050202516252520036080000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050202416242420036080000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050202416252520036080000102004020040200402004020040