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 S)

Test 1: uops

Code:

  fcvt s0, 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
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110001673116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723156125472510001000100039816013022303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100013073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372366125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvt s0, 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)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)9fa7a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954725101001001000010010000500427716013001830037300372826432874510100200100002001017430037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
1020430037224006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100002107101161129633100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000288607101161129633100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300841110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038

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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000006404163329629010000103003830038300383003830038
100243003722500000007262954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000100006403243329629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030131300371110021109101010000104420019585207875724529880210000103012230357303223036730358
10024302712270026933616052502948413310072141005616110508242852721302343041530369283163328899110662211140201132230368300848110021109101010000100001020648007944724429881310000103036930371303703036230368
1002430368227017793361605772294841681007614100641311200824287976130306304633041428315382892811212221147124114593046330460101100211091010100001040212250836068541015529980210000103046330466304173045230319
100243041722811821068704152072946619010086121006420112007742890261303063045530452283173728935113622011174221146930463304159110021109101010000100201225280208324546329953410000103046230464304603046630464
1002430411227019979261607872954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000006403163329629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000006403163329629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000006403163329629010000103003830085300383003830038
10024300372250000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000006403163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvt s0, d8
  fcvt s1, d8
  fcvt s2, d8
  fcvt s3, d8
  fcvt s4, d8
  fcvt s5, d8
  fcvt s6, d8
  fcvt s7, 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)03081e3f51inst 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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611500030258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010003011151181160020036800001002004020040200402004020040
802042003915000177258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391500093258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010003011151180160020036800001002014020040200402004020040
80204200391500030258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010001888011151180160020036800001002004020040200402004020040
802042003915000328258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010000211151180160020036800001002004020040200402004020040
80204200391500030258010810080008100801305006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010000011151180161020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391500095258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 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)6061696b6d6edispatch 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)9faccfd0d2itlb miss (d4)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915012402580010108000010800005064000000200200200392003999963100198001020800002080000200392003911800211091010800001005020003141612102003680000102004020040200402004020040
80024200391500218258001010800001080000506400000020020020039200399996310019800102080000208000020039200391180021109101080000100502000110161272003680000102004020040200402004020040
8002420039150040258001010800001080000506400000020020020039200399996310019800102080000208000020039200391180021109101080000100502000191612122003680000102004020040200402004020040
8002420039150063258001010800001080000506400000020020020039200399996310019800102080000208000020039200391180021109101080000100502000281611112003680000102004020040200402004020040
80024200391500402580010108000010800005064000000200200200392003999963100198001020800002080000200392003911800211091010800001005020030161611122003680000102004020040200402004020040
80024200391500632580010108000010800005064000005200200200392003999963100198001020800002080000200392003911800211091010800001005020533122511122003680000102004020040200402019320040
800242003915201277258001010800001080000506400000520020020039200399996310019800102080000208000020039200391180021109101080000100502000291611112003680000102004020040200402004020040
80024200391501240258001010800001080000506400000520020020039200399996310019800102080000208000020039200391180021109101080000100502003161612122003680000102004020040200402004020040
80024200391500126258001010800001080000506400000020020020039200399996310019800102080000208000020039200391180021109101080000100502050061610112003680000102004020040200402004020040
8002420039150040258001010800001080000506400000020020020039200391001431001980010208000020800002003920039118002110910108000010350200018161072003680000102004020040200402004020040