Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINT64X (vector, 2S)

Test 1: uops

Code:

  frint64x v0.2s, v0.2s
  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)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696b6d6edispatch 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)a0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372308225472510001000100039816003018030373037241432895100010001000303730371110011000000073216112629100030383038303830383038
100430372306125472510001000100039816003018030373037241432895100010001000303730371110011000000373116112629100030383038303830383038
1004303723126125472510001000100039816003018030373037241432895100010001000303730371110011000000073116112629100030383038303830383038
100430372406125472510001000100039816003018030373037241432895100010001000303730371110011000000073116112629100030383038303830383038
1004303724012425472510001000100039816003018030373037241432895100010001000303730371110011000000073116112629100030383038303830383038
100430372306125472510001000100039816013018030373037241432895100010001000303730371110011000000073116112629100030383038303830383038
100430372406125472510001000100039816013018030373037241432895100010001000303730371110011000000073116112629100030383038303830383038
100430372406125472510001000100039816013018030373037241432895100010001000303730371110011000000073116112629100030383038303830383038
1004303724022925472510001000100039816003018030373037241432895100010001000303730371110011000000073116112629100030383038303830383038
100430372308425472510001000100039816013018030373037241432895100010001000303730371110011000000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frint64x v0.2s, 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)0318191e3f4e51inst 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)9fa8accfd5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233000274295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011601129633100001003003830038300383003830038
1020430037233000705295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011601129633100001003003830038300383003830038
1020430037233000279295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011601129633100001003003830038300383003830038
102043003723300061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011601129633100001003003830038300383003830038
1020430037232110726295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011601129633100001003003830038300383003830038
102043003723300061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011601129633100001003003830038300383003830038
102043003723300061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011651129633100001003003830038300383003830038
102043003724300061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011601129633100001003003830038300383003830038
1020430037233000103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011601129633100001003003830038300383003830038
102043003723200061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011601129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e1f3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372320006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640416222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372240006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000640216222966710000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250906129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002210910101000010000640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018030037300372828632878810010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250906129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frint64x v0.2s, v8.2s
  frint64x v1.2s, v8.2s
  frint64x v2.2s, v8.2s
  frint64x v3.2s, v8.2s
  frint64x v4.2s, v8.2s
  frint64x v5.2s, v8.2s
  frint64x v6.2s, v8.2s
  frint64x v7.2s, v8.2s
  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)030b181e3f51inst 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)9fa0a6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420049155000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000041201115118216002003600800001002004020040200402004020040
802042011315600030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115204077002003600800001002004020040200402004020040
802042003915500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100005601115118016002003600800001002004020040200402004020040
8020420039155000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000029001115118016002003600800001002004020040200402004020040
8020420039156000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000030001115118016002003600800001002004020040200402004020040
802042003915500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100004301115118016002003600800001002004020040200402004020040
8020420039155000302580108100800081008002050064013202002020039200399977699908012020080136200800322003920039118020110099100100800001000038001115118016002003600800001002004020040200402004020040
802042003915500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016002003600800001002004020040200402004020040
8020420039161000582580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000021201115118016102003600800001002004020040200402004020040
802042003915600030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016002003600800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080a18191e1f3f51inst 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)5d5f60696d6edispatch 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)9fa0a1a6a8a9acc2c9cfd0d5d6dadbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501560000004025800101080000108000050640000000200202003920039999631001980010208000020800002003920039118002110910108000010000000005020612160011132003680000102004020040200402004020040
800242003915500000045525800101080000108000050640000000200202003920039999631001980010208000020800002003920039118002110910108000010000000005020010160011112003680000102004020040200402004020040
80024200391550000004025800101080000108000050640000000200202003920039999631001980010208000020800002003920039118002110910108000010000000005020012160012112003680000102004020040200402004020040
80024200391550000004025800101080000108000050640000000200202003920039999631001980010208000020800002003920039118002110910108000010000000005020011160011132003680000102004020040200402004020040
800242003915500000040258001010800001080000506400000002002020039200399996310019800102080000208000020039200391180021109101080000100000018005020013160013112003680000102004020040200402004020177
80024200391560000004025800101080000108000050640000000200202003920039999631001980010208000020800002003920039118002110910108000010020100005020012160010132003680000102004020040200402004020040
800242003915500000040258001010800001080000506400000002002020039200399996310019800102080000208000020039200391180021109101080000100000012005020012160011112003680000102004020040200402004020040
800242003915500000040258001010800001080000506400000002002020039200399996310019800102080000208000020039200391180021109101080000100000027005020013160013132008480000102004020040200402004020040
80024200391550000004025800101080000108000050640000000200202003920039999631001980010208000020800002003920039118002110910108000010000000005020012160012112003680000102004020040200402004020040
800242003915600000040258001010800001080000506400000002002020039200399996310019800102080000208000020039200391180021109101080000100000027005020011160013112003680000102004020040200402004020040