Apple M1 Microarchitecture Research by Dougall Johnson

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

FADDP (scalar, D)

Test 1: uops

Code:

  faddp d0, v0.2d
  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)033f4e51inst 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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723822547251000100010003981601301830373037241432895100010002000303730371110011000075116112629100030383038303830383038
1004303723612547251000100010003981601301830373085241432895100010002000303730371110011000073116112629100030383038303830383038
10043037231452547251000100010003981601301830373037241432895100010002000303730371110011000073116112629100030383038303830383038
1004303722842547251000100010003981601301830373037241432895100010002000303730371110011000075116112629100030383038303830383038
1004303723842547251000100010003981601301830373037241432895100010002000303730371110011000073116112629100030383038303830383038
1004303723612547251000100010003981601301830373037241432895100010002000303730371110011000073116112629100030383038303830383038
10043037221032547251000100010003981601301830373037241432895100010002000303730371110011000073116112629100030383038303830383038
1004303723842547251000100010003981601301830373037241432895100010002000303730371110011000075116112629100030383038303830383038
1004303723612547251000100010003981601301830373037241432895100010002000303730371110011000073116112629100030383038303830383038
1004303723612547251000100010003981601301830373037241432895100010002000303730371110011000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  faddp d0, v0.2d
  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)60696b6d6edispatch 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954725101001001000010010000500427716003001803003730037282716287411010020010008200200163003730037111020110099100100100001000011171801600296450100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001803003730037282716287411010020010008200200163003730037111020110099100100100001000011171701600296450100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716003001803003730037282716287411010020010008200200163003730037111020110099100100100001003011171701600296450100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001803003730037282717287411010020010008200200163003730037111020110099100100100001000011171701600296450100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716003001803003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001803003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225150612954725101001001000010010000500427716003001803003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716003001803003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830087
102043003722500612954725101001001000010010000500427716003001833003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001803003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000012082629547251001010100001010000504277160300183003730037282862128767100102010000202000030037300371110021109101010000100000103006403163329629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716030018300373003728286328767100102010000202000030037300371110021109101010000100000000006403163329629010000103003830038300383003830038
100243003722500000027442954725100101010000101000050427716030018300373003728286328767100102010000202000030037300371110021109101010000100000000006403163329629010000103003830038300383003830038
10024300372250000001032954725100101010000101000050427716030018300373003728286328767100102010000202000030037300371110021109101010000100000000006403163329629010000103003830038300383003830038
100243003722500000020762954725100101010000101000071427716030054300373003728293328767100102010000202000030085300841110021109101010000100000000006403163329629010000103003830038300383003830038
100243003722500000886129547621001010100001110000504277160300183003730037282963287671001020100002020000300373003711100211091010100001000001012006403163329629010000103003830038300383003830038
10024300372250000120612954725100101010000101000077427716030018300373003728286328767100102010000202000030037300371110021109101010000100000000006403163329629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716030018300373003728286328767100102010000202000030037300371110021109101010000100000000006403163329629010000103003830038300383003830038
100243003722400001207262954778100101010000101000050427716030018300373003728286328767100102010000202000030037300371110021109101010000100000000006403163329629010000103003830038301803003830038
1002430037226000000612954725100101010000101000050427716030018300373003728286328767100102010000202000030037300371110021109101010000100000000006403164529629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  faddp d0, v8.2d
  faddp d1, v8.2d
  faddp d2, v8.2d
  faddp d3, v8.2d
  faddp d4, v8.2d
  faddp d5, v8.2d
  faddp d6, v8.2d
  faddp d7, v8.2d
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)0307191e1f3f51inst 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)9fa0a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420049150000030258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010003011151181160020036800001002004020040200402004020040
8020420039150000030258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151184160420036800001002004020040200402004020040
8020420039150000064258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150000030258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151180164420036800001002004020040200402004020040
802042003915010026430258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150000030258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150000030258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150000030258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150000030258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150000030258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010001011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3f51inst 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)9fa8acbranch mispredict (cb)cfd0d5d6d9ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001003050200116011200366880000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050200116011200364980000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050200116011200368780000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050200116011200367280000102004020040200402004020040
800242003915012040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050200116011200367280000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001003050200116011200367280000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050200116011200367280000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050200116011200367280000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001030050200116211200367680000102004020040200402004020040
800242003915000325258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050200116011200367280000102004020040200402004020040