Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVT (D to H)

Test 1: uops

Code:

  fcvt h0, 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)03191e1f3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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
1004303722000612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723000612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303722000612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723000612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230120612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303722090612547251007100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723000612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230240612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303722060612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723060612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvt h0, 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)031e1f3a3f4e51inst 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)9fa0a6a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037224000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000020371011611296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000371011611296330100001003003830038300383003830038
10204300372240006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000390371011611296330100001003003830038300383003830038
1020430037224000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011621296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000010371011611296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000010371011611296330100001003003830038300383003830038
10204300372250006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000550971011611296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000010371011610296330100001003003830038300383003830038
1020430037225000942954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110202100991001001000010000000371011611296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000010371011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03091e3f4e51inst 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
100243003722510612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010100640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722500612954798100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010400640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640216222968910000103003830038300383003830038
100243003722500612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010300640216222962910000103003830038300383003830038
100243003722506612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvt h0, d8
  fcvt h1, d8
  fcvt h2, d8
  fcvt h3, d8
  fcvt h4, d8
  fcvt h5, d8
  fcvt h6, d8
  fcvt h7, 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)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)9fa6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150030258010810080088100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100030111511811600200361800001002004020040200402004020040
8020420039150030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100100111511801600200360800001002004020040200402004020040
8020420039150030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511801600200360800001002004020040200402004020040
8020420039150030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511801600200360800001002004020040200402004020040
8020420039150030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511801600200360800001002004020040200402004020040
8020420039150030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511801600200360800001002004020040200402004020040
8020420039150030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511801600200360800001002004020040200402004020040
8020420039150030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511801600200360800001002004020040200402004020040
8020420039150040258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100006111511801600200360800001002004020040200402004020040
8020420039150030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511801600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03041e3f51inst 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)9fa0a8accdcfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015000402580010108000010800005064000012002020039200399996031001980010208000020800002003920039118002110910108000010000050202716025242003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996031001980010208000020800002003920039118002110910108000010000050202549025252003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996031001980010208000020800002003920039118002110910108000010000050201716021162003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996031001980010208000020800002003920039118002110910108000010000050202516014252003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996031001980010208000020800002003920039118002110910108000010000050202516028262003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996031001980010208000020800002003920039118002110910108000010000050201216025182003680000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000100580050202716027142003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996031001980010208000020800002003920039118002110910108000010000050201616026152003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996031001980010208000020800002003920039118002110910108000010000050202716014272003680000102004020040200402004020040
800242003915003402580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010000050202716028212003680000102004020040200402004020040