Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTZU (scalar, fixed-point, D to D)

Test 1: uops

Code:

  fcvtzu d0, d0, #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)030b1e3f4e51inst 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)e0ec? fp/simd (ee)f5f6f7f8fd
100430372400103254725100010001000398160130183037303724143289510001000100030373037111001100000731161126290100030383038303830383038
10043037240061254725100010001000398160130183037303724143289510001000100030373037111001100010731161126290100030383038303830383038
100430372300103254725100010001000398160130183037303724143289510001000100030373037111001100010731161126290100030383038303830383038
10043037240061254725100010001000398160030183037303724143289510001000100030373037111001100000731161126290100030383038303830383038
10043037240061254725100010001000398160130183037303724143289510001000100030373037111001100000731161126290100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000731161126290100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000731161126290100030383038303830383038
10043037240061254725100010001000398160030183037303724143289510001000100030373037111001100000731161126290100030383038303830383038
10043037230061254725100010001000398160130183037303724143289510001000100030373037111001100000731161126290100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000731161126290100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzu d0, d0, #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)030b18191e1f3f4e51inst 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)9fa1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000046060710116112963300100001003003830038300383003830038
102043003724500000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000065000710116112963300100001003003830038300383003830038
102043003723300000612953725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000039060710116112963300100001003003830038300383003830038
1020430037232000007262954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000044000710116112963320100001003003830038300383003830038
1020430037232000906129547251010010010000100100005004277160030018300373003728264628763101002001000020010000300373003711102011009910010010000100000420007101161129633110100001003003830038300383003830038
102043003723300000612954725101001001000010010000500427716003005430037300372826432874510100200100002001000030037300371110201100991001001000010000062000710116112963300100001003003830038300383003830038
102043003723300012061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000004000710116112963300100001003003830038300383003830038
102043003723300041706129547251010010010000100100005004277160130018300373003728264232874510100200100002001000030037300371110201100991001001000010000058000710116112963300100001003003830038300383003830038
102043003723300000612954725101251001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000069000710216112963300100001003003830038300383013530038
10204300372330002701262954725101001001000012210000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000046060710116112963300100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03040b191e1f3f4e51inst 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
100243003722510000712954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229690010000103003830038300383003830038
1002430037225000002082954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229667010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722400000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162129629010000103003830038300383003830038
1002430037225000001032954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
1002430037224000007262954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000055427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzu d0, d8, #3
  fcvtzu d1, d8, #3
  fcvtzu d2, d8, #3
  fcvtzu d3, d8, #3
  fcvtzu d4, d8, #3
  fcvtzu d5, d8, #3
  fcvtzu d6, d8, #3
  fcvtzu d7, d8, #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)0318191e3f51inst 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)9fa6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0e8? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200681550002512580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100006111511821633200360800001002004020040200402004020040
80204200391551012532580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000111511831633200360800001002004020040200402004020040
80204200391550002232580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000111511831633200360800001002004020040200402004020040
8020420039156000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000111511831643200360800001002004020040200402004020040
80204200391550001352580108100800081008002050064013212002020039200399977069990801202008003220080032200392003911802011009910010080000100000111511841634200360800001002004020040200402004020040
8020420039155000512580108100800081008002050064013212002020039200399977069990801202008003220080032200392003911802011009910010080000100000111511843743200360800001002004020040200402004020040
8020420039156000932580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100020111511841634200360800001002004020040200402004020040
8020420039156000932580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000111511841643200360800001002004020040200402004020040
80204200391550001562580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000111511841624200360800001002004020040200402004020040
8020420039155000932580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000111511831644200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f5051inst 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)9fa0a1a8acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511550075120023258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000373050200001516000166200360080000102004020040200402004020040
800242003915600402002325800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100000050200001616000616200360080000102004020040200402004020040
80024200391550047120023258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000130502230016162111552003615080000102004020040200402004020040
800242003915500400258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000015050200001616000166200360080000102004020040200402004020040
80024200391550558400258001010800001080000506400000120020200392003910005310019800102080000208000020039200391180021109101080000100003050200001616000166200360080000102004020040200402004020040
80024200391551040025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100020050200001616200166200360080000102004020040200402004020040
8002420039156004002580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000605020000516000166200360080000102004020040200402004020040
80024200391550040025800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100040005020000616000616200360080000102004020040200402004020040
80024200391550075802580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000005020000616000166200360080000102004020040200402004020040
8002420039155012400258001010800001080000506400000020020200392003999963100198001020800002080000200392019011800211091010800001000100502000016160001616200360080000102004020040200402004020040