Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTNS (scalar, D to D)

Test 1: uops

Code:

  fcvtns 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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723082254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037240103254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230501254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724061254725100010001000398160030183037303724143289510001000100030373037111001100000073216112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100020073116112629100030383038303830383038
10043037240151254725100010001000398160030183037303724143289510001000100030373037111001100000073216212629100030383038303830383038
100430372312412254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtns 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)030f18191e1f3f4e51inst 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)6061696d6edispatch 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233000831061295472510100100100001001000050042771601030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071001161129633100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771601030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071001161129633100001003003830038300383003830038
102043003723300000156295472510100100100001001000050042771601030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071001161129633100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771601030037300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071001161129633100001003003830038300383003830038
1020430037233000144061295472510100100100001001000050042771601030018300373003728264328745101002001000020010000300373003711102011009910010010000100000103000071001161129633100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771601030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071001161129633100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771601030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071001251129633100001003003830038300853003830038
1020430037233002168061295472510100100100001001000050042771600030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071001161129633100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771601030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000020071001161129633100001003003830038300383003830038
102043003723200000251295472510100100100001001000050042771601030018300373003728264328749101002001000020010000300373003711102011009910010010000100000000000071001161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e3f4e51inst 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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372330186129547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
1002430037232006129547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
1002430037233006129547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
1002430037232006129547251001010100001010000504277160030018300373003728286032876710010201000020100003003730178111002110910101000010000006403163329629010000103003830038300383003830038
10024300372410053629547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
10024300372250072629547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010003066403163329629210000103003830038300383003830038
10024300372331330329547251001010100001010000504277160130054300373003728286032876710010201000020100003003730037111002110910101000010001066403163329629010000103003830038300383003830038
100243003722502112629547251001010100001010000504277160130018300373003728286032876710010201000020100003016630037111002110910101000010000006403163329629010000103003830038300383003830038
10024300372250010329547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtns d0, d8
  fcvtns d1, d8
  fcvtns d2, d8
  fcvtns d3, d8
  fcvtns d4, d8
  fcvtns d5, d8
  fcvtns d6, d8
  fcvtns 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)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)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)9fa8acc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200491552472258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160200360800001002004020040200402004020040
80204200391552130258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000311151180160200360800001002004020040200402004020175
80204200391560695258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160200360800001002004020040200402004020040
8020420039155930258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160200360800001002004020040200402004020040
80204200391563930258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160200360800001002004020040200402004020040
8020420039155630258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160200360800001002004020040200402004020040
8020420039155930258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160200360800001002004020040200402004020040
8020420039155030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160200360800001002004020040200402004020040
80204200391551830258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160200360800001002004020040200402004020040
80204200391552730258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307081e3f51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915500068258001010800001080000506400000200200200392003999963100198022120800002080000200392003911800211091010800001000050201616782003680000102004020040200402004020040
80024200391560004025800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000101005020616962003680000102004020040200402004020040
8002420039155009040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000050208167102003680000102004020040200402004020040
8002420039155003951525800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000100005020916782003680000102004020040200402004020040
8002420039155005740258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000050206161092003680000102004020040200402004020040
800242003915500394025800101080000108000050640000020020020039200399996310019801222080000208000020039200391180021109101080000100005020516682003680000102004020040200402004020040
80024200391560004025800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000100005020516862003680000102004020040200402004020040
800242003915600544025800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000100005020816982003680000102004020040200402004020040
800242003915600394025800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000100005020716852003680000102004020040200402004020040
8002420039156008440258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000050209161092003680000102004020040200402004020040