Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTI (scalar, D)

Test 1: uops

Code:

  frinti 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)a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372345612547251000100010003981600301830373037241432895100010001000303730371110011000048073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289511501000100030373037111001100000073116112629100030383038303830383038
1004303724061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037231261254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230612547251000100010003981601301830373037241432895100010001000303730371110011000048073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frinti 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)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)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)9fa1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037232000103295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000400071011611296330100001003003830038300383003830038
1020430037232000213295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000100071011611296330100001003003830038300383003830038
102043003723200061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000180071011611296330100001003003830038300383003830038
102043003723300061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003723200061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000003071011611296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010004300071011611296330100001003003830038300383003830038
1020430037232000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010005500071011611296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010001060710116112963321100001003018030038300383003830038
1020430037233000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010002702771071011611296330100001003003830038300383003830133

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa1a6a8acc2c5cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037232000000082295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000900006402162229629010000103003830038300383003830038
10024300372330000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010002660006402162229629010000103003830038300383003830038
10024300372320000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010001960006402162229629010000103003830038300383003830038
10024300372330000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010001430006402162229629010000103003830038300383003830038
1002430037233000000061295472510010101000013100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000800006402162229629010000103003830038300383003830038
1002430037233000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003723300000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100015120006402162229629010000103003830038300383003830038
10024300372330000120061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000960006402162229629010000103003830038300383003830038
10024300372320000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010003330006402162229629010000103003830038300383003830038
100243003723200000006129547251001010100001110000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100065210006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frinti d0, d8
  frinti d1, d8
  frinti d2, d8
  frinti d3, d8
  frinti d4, d8
  frinti d5, d8
  frinti d6, d8
  frinti 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)03080b18191e1f3f51inst 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)9fa0a1a6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915600000058258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003915500000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000030111511801600200360800001002004020040200402004020040
802042003915500000072258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003915500000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
8020420039155000012051258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003915500000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000100111511801600200360800001002004020040200402039820040
802042003916100000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000300111511801600200360800001002004020040200402004020040
802042003915500000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003915500000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003915500000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080f191e3f51inst 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)9fa6a7a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050155000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000050205165220036080000102004020040200402004020040
800242003915500004025802061080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100026810050203162420036080000102004020040200402004020040
8002420039156000040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000000050202165220036080000102004020040200402004020040
8002420039156000040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000000050205164420036080000102004020040200402004020040
8002420039156000340258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000000050205164520036080000102004020040200402004020040
8002420039155000040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000000050205162420036080000102004020040200402004020040
80024200391560000402580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010004200050202165320036080000102004020040200402004020040
8002420039155000040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000100050204165220036080000102004020040200402004020040
8002420039155000040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000100050204164320036080000102004020040200402004020040
80024200391610000303258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010791671000000050202165420036080000102004020040200402004020040