Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTM (scalar, D)

Test 1: uops

Code:

  frintm d0, d0
  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
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372307025472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723126125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723010325472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintm d0, d0
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723200538295472510125125100001251000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100017171011611296330100001003003830038300383003830038
1020430037233006129547251010010010000125100006264277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010015471011611296330100001003003830038300383003830038
10204300372320061295472510100125100001251000062642771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100018071011611296330100001003003830038300383003830038
10204300372341077429547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010002171221611296330100001003003830038300383003830038
102043003723300612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000671221722296330100001003003830038300383003830038
10204300372330127262954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001002071211611296330100001003003830038300383003830038
1020430037232002042954725101001001000010010000626427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037233012612954725101251251000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000371011611296330100001003003830038300383003830038
102043003723410612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000144712316212963325100001003003830038300383003830038
10204300372330061295472510100100100001001000062642771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100015371011612296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080a0b18191e1f3a3f4e51inst 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)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)9fa0a1a6a7a8a9acc2cfd2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037233000000120082295472510010101000010100005042771600300183003730037282860328767100102010000201000030037300371110021109101010000100300000064003163329629010000103003830038300863003830038
10024300372320000000132082295472510010101000010100005042771600300183003730037282860328767100102010000201000030037300371110021109101010000100000000064003163329629010000103003830038300383003830038
1002430037233000000300612954725100101010000101000050427716003001830037300372828601828767100102010000201000030037300371110021109101010000100000000275301288131129917010000103003830038300383003830133
10024301792342101101013297921552295299910071111004810100005042771601304143050830557283200502895211512221147324116273051030368111100211091010100001002300427945088206978530025110000103060730513305593055730546
1002430321236011071014529680663529448225100701710088121150010342771600300183003730037282860328767100102010000201000030037300371110021109101010000104400000064003163329629010000103003830038300383003830038
1002430037233000000000166295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100000000064003163329629010000103003830038300383003830038
100243003723300000000061295472510010101000010100005042771600300183003730037282860328767100102010000201000030037300371110021109101010000100000000064003163329629010000103003830038300383003830038
100243003722500000000061295472510010101000010100005042771600300183003730037282860328767100102010000201000030037300371110021109101010000100000000064003163329629010000103003830038300383003830038
100243003722500000000061295472510010101000010100005042771600300183003730037282860328767100102010000201000030037300371110021109101010000100000000064003163329629010000103003830038300383003830038
100243003722500000000061295472510010101000010100005042771600300183003730037282867328767100102010000201000030037300371110021109101010000100000000064003163629629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintm d0, d8
  frintm d1, d8
  frintm d2, d8
  frintm d3, d8
  frintm d4, d8
  frintm d5, d8
  frintm d6, d8
  frintm d7, d8
  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)0307080a18191e1f3a3f51inst 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)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)9fa0a7a8a9acc5branch mispredict (cb)cdcfd6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915500000000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000001115118160020036800001002004020040200402004020040
80204200391560000000030258010810080008100800205006401320200202003920039997706999080120200800322008003220091200391180201100991001008000010000004661115118160020036800001002004020040200402004020040
802042003915500001000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000001115118160020036800001002004020040200402004020040
802042003915600000000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000001115118160020036800001002004020040200402004020040
802042003915500001000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000001115118160020036800001002004020040200402004020040
802042003915500000000302580108100800081008002050064013202002020039200399986069990801202008003220080032200392003911802011009910010080000100000001115118160020036800001002004020040200402004020040
802042003915500000000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000031115118160220036800001002004020040200402004020040
8020420039155000000003025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000015061115118160020036800001002004020040200402004020040
802042003916000000000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000001115118160020036800001002004020040200402004020040
802042003915500000000302580108100800081008002050064013212002020039200399977069990801202008003220080032202502003911802011009910010080000100000001115118160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b193f51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391550000822580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100905020316552003680000102004020040200402004020040
8002420039155000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010017405020316662003680000102004020040200402004020040
800242003915500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001005705020516632003680000102004020040200402004020040
80024200391560000402580010108000010800005064000002002020039200399996310019801162080000208000020039200391180021109101080000100005020316832003680000102004020040200402004020040
80024200391551000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100605020316322003680000102004020040200402004020040
800242003915600008225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001001205020316662003680000102004020040200402004020040
80024200391560000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000101605020316322003680000102004020040200402004020040
80024200391550000862580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100605020616232003680000102004020040200402004020040
80024200391560000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100305020716672003680000102004020040200402004020040
80024200391550000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100305020316322003680000102004020040200402004020040