Apple M1 Microarchitecture Research by Dougall Johnson

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

UCVTF (scalar, fixed-point, S from S)

Test 1: uops

Code:

  ucvtf s0, s0, #3
  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)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)a0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372308225472510001000100039816030183037303724143289510001000100030373037111001100000073216112629100030383038303830383038
100430372406125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372406125472510001000100039816030183037303724143291410001000100030373037111001100000073216222629100030383038303830383038
100430372406125472510001000100039816030183037303724143289510001000100030373037111001100001073216222629100030383038303830383038
1004303724056025472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372406125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372406125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303724047225472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372406125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  ucvtf s0, s0, #3
  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)03080b18191e3f4e51inst 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723200000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
102043003723200000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
102043003723300000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
102043003723200000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
10204300372330000124412954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
102043003723200000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
102043003723200000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
102043003723200000612954725101001001000011310000500427716003001830037300372826432874510100200100002021000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
102043003723300000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
1020430037233000002512954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500193295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372250082295472510010101000010100005042771602300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722500726295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722500726295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722500797295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828626287561001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372240061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  ucvtf s0, s8, #3
  ucvtf s1, s8, #3
  ucvtf s2, s8, #3
  ucvtf s3, s8, #3
  ucvtf s4, s8, #3
  ucvtf s5, s8, #3
  ucvtf s6, s8, #3
  ucvtf s7, s8, #3
  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)03080b191e1f3f51inst 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)9fa0a1a6a8a9acc5branch mispredict (cb)cdcfd5d6dde0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003915500000995258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160200360800001002004020040200402004020143
8020420039155000917630258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000000011151530160200360800001002004020040200402004020040
802042003915500000410258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160200360800001002004020040200402020620040
802042003915500000302580108100800081008002050064013202002002003920039100136999080120200800322008003220039200391180201100991001008000010000000011151180160200360800001002004020040200402004020040
80204200391550000030258018410080008100800205006401320200200200392003999776999080120200800322028003220039200391180201100991001008000010000000011151180160200360800001002004020040200402004020040
80204200391560000030258010810080008100800205006401320200200200392003999776999080120200802452008003220039200391180201100991001008000010000000011151180160200360800001002004020040200402004020040
80204200391550000030258010810080008100800205006401321200203200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160200360800001002004020040200402004020094
80204200391550000030258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160200360800001002004020040200402004020040
80204200391550000030258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160200360800001002004020040200402004020040
80204200391550003030258010810080008100800205006401320200200200392003999776999080335200800322008003220039200391180201100991001008000010000000611151180160200360800001002004020040200402004020040

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)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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401550040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100105020216222003680000102004020040200402004020040
800242003915500141258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020316222003680000102004020040200402004020040
80024200391550040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020216322003680000102004020040200402004020040
80024200391560040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020216222003680000102004020040200402004020040
80024200391550040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100105020316222003680000102004020040200402004020040
80024200391550040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020216222003680000102004020040200402004020040
80024200391550040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020416322003680000102004020040200402004020040
80024200391550040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020316232003680000102004020040200402004020040
800242003915512040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020216232003680000102004020040200402004020040
80024200391550040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100035020216222003680000102004020040200402004020040