Apple M1 Microarchitecture Research by Dougall Johnson

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

UCVTF (vector, integer, 4H from 4H)

Test 1: uops

Code:

  ucvtf v0.4h, v0.4h
  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)030b1e1f3f4e51inst 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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723000612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
10043037230001032547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723000612547251000100011463981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
10043037220120612547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723000612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
10043037230001112547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723000612547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723000612547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303722000612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723000612547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  ucvtf v0.4h, v0.4h
  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)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)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)9fa8acc2c5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372331830612954725101001001000010010000500427716000300183003730084282643287451010020010000200100003003730037111020110099100100100001000000007100116112963300100001003003830038300383003830038
1020430037232150612954725101001001000010010000500427716010300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007100116112963300100001003003830038300383003830038
10204300372332101972954725101001001000010010000500427716010300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007100116112963300100001003003830038300383003830038
1020430037233001042954725101001001000010010000500427716010300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007100116112963300100001003003830038300863013430038
102043003723300612954725101001001000010010000500427716000300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007100116112963300100001003003830038300383003830038
10204300372331501032954725101001001000010010000500427716010300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007100116112963300100001003003830038300383003830038
1020430037233450612954725101001001000010010000500427716010300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007100116112963300100001003003830038300383003830038
1020430084233180612954725101001001000010010000500427716000300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007100116112963300100001003003830038300383003830038
1020430037233210612954725101001001000010010000500427716000300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007100116112963300100001003003830038300383003830038
102043003723327011262954725101001001000010010000500427716010300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007100116112963300100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)5e60696d6edispatch 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)9fa8a9accfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003723200576061295472510010101000010100005042771600130018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
10024300372330024061295472510010101000010100005042771600030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
10024300372320087061295472510010101000010100005042771600030018300373003728286328767100102010000201000030037300371110021109101010000100036402162229629010000103003830038300383003830038
1002430037233002460551295472510010101000010100005042771600030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003723300240061295472510010101000810100005042771600130018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003723300318061295472510010101000010100005042771600130018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
1002430037233101590103295472510010101000010100005042771600130018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
1002430037233003450362295472510010101000010100005042771600130018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
10024300372320030061295472510010101000010100005042771600130018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003723300426061295472510010101000010100005042771600130018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  ucvtf v0.4h, v8.4h
  ucvtf v1.4h, v8.4h
  ucvtf v2.4h, v8.4h
  ucvtf v3.4h, v8.4h
  ucvtf v4.4h, v8.4h
  ucvtf v5.4h, v8.4h
  ucvtf v6.4h, v8.4h
  ucvtf v7.4h, v8.4h
  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)03080b18191e1f3f51inst 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)9fa1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059155000100302580108100800081008002050064013202002020039200399986699908012020080032200800322003920039118020110099100100800001000000001115118016002003600800001002004020040200402004020040
8020420114156000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016002003600800001002004020040200402004020040
8020420039155000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016002003600800001002004020040200402004020040
80204200391550000120302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016002003600800001002004020040200402004020040
8020420039155000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016002003601800001002004020040200402004020040
8020420039155000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016002003600800001002004020040200402004020040
80204200391610000390302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016002003600800001002004020040200402004020040
8020420039155000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016002003600800001002004020040200402004020040
8020420039155000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016002003600800001002004020040200402004020040
8020420039155000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016002003600800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030918191e1f3f51inst 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)9fa6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051155000110488219225800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000005020231621212003680000102004020040200402004020040
800242003915500021040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100000050209162192003680000102004020114200402004020040
80024200391610000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100000050209169212003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000005020211621212003680000102004020040200402004020040
800242003915500000402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000002502021169212003680000102004020040200402004020040
800242003915500024040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100000050209162192003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000005020211621212003680000102004020040200402004020040
8002420039156000004025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000005020211621212003680000102004020040200402004020040
80024200391550004804025800101080000108000050640000200202003920039999631001980010208000020800002003920092718002110910108000010000005020101619142003680000102004020040200402004020040
800242003915500000402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000000502022162192003680000102004020040200402004020040