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, fixed-point, 2S from 2S)

Test 1: uops

Code:

  ucvtf v0.2s, v0.2s, #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)0307090b181e1f3f4e51inst 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
1004303723000000612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303724000000822547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723000000612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723000000612547251000100010003981601301830373037241432895100010001000303730371110011000073116112841100030383038303830383038
1004303723000000612547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723000000612547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723000000612547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723000000612547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
10043037240000001562547251000100010003981601301830373037241432895100010001000303730371110011000073116112782100030383038303830383038
1004303724000000612547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  ucvtf v0.2s, v0.2s, #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)0307080b18191e1f3f4e51inst 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)9fa8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300000006129547251010010010000100100005004277160103001830037300372826432874510100200100002001000030037300371110201100991001001000010016710002162229633100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010003710002162229633100001003003830038300383003830038
102043003723200000001427295472510100100100001001000050042771601030018300373003728264328745101002001000020010000300373003711102011009910010010000100269710002162229633100001003003830038300383003830038
1020430037233000000061295472510100100100001001000050042771600030018300373003728264328745101002001000020410000300373003711102011009910010010000100270710002162229633100001003003830038300383003830038
1020430037232000001206129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010056710002162229633100001003003830038300383003830038
1020430037233000000061295472510100100100001001000050042771600030018300373003728264328745101002001000020010000300373003711102011009910010010000100280710002162229633100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010026710002162229633100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160103001830037300372826432874510100200100002001000030037300371110201100991001001000010010710002162229633100001003003830038300383003830218
102043003723300000006129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010013710002162229633100001003003830038300383003830038
1020430037233000000061295472510100100100001001000050042771601030018300373003728264328745101002001000020010000300373003711102011009910010010000100550710002162229633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03090b18191e1f3a3f4e51inst 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)9fa0a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372330000390061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000004640216222977310000103003830038300383003830038
10024300372330000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010028060640216222962910000103003830038300383003830038
100243003723300000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100001710640216222962910000103003830038300383003830038
1002430037232000000061295472510010101000010100005042771600300183003730037282863287671001620100002010000300373003711100211091010100001020000660216222962910000103017730038300843008530132
1002430119233100100161295384410010111000810101505042798640300543003730037282907287671001020101682410000300843003711100211091010100001002000661216222962910000103003830038300383003830216
1002430084232100010588089295382510010111000810100005042771600300903008330037282863287671001020100002010000300373003711100211091010100001000202640316232962910000103003830038300743003830038
10024300372330101000612954761100101010000101000050427716013001830037300372828632876710010201000024100003003730037111002110910101000010024064640224222962910000103008530038300853003830085
100243003723300000006129529251003010100161110150504277160130018300843003728286328767100102010000201000030037300371110021109101010000100001290640216222962910000103003830038300383003830038
1002430037233001013200612954725100101110000121000050427851213001830037300372828632876710010201000020100003003730037111002110910101000010026060640216222962910000103008530038300383003830038
1002430132233000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000002640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  ucvtf v0.2s, v8.2s, #3
  ucvtf v1.2s, v8.2s, #3
  ucvtf v2.2s, v8.2s, #3
  ucvtf v3.2s, v8.2s, #3
  ucvtf v4.2s, v8.2s, #3
  ucvtf v5.2s, v8.2s, #3
  ucvtf v6.2s, v8.2s, #3
  ucvtf v7.2s, v8.2s, #3
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)0307090a1e3f51inst 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)9fa1a8acc5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581551011230258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118011611200360800001002004020040200402004020040
8020420039155101030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118011611200360800001002004020040200402004020040
8020420039155101972258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118011611200360800001002004020040200402004020040
8020420039155101030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118011611200360800001002004020040200402004020040
8020420039156101030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118011611200360800001002004020040200402019620040
8020420039155101030258010810080008100800205006401322002020039200399977699908012020080032200800322011320039118020110099100100800001000001115118011611200360800001002004020040200402004020040
8020420039161101030258010810080008100800205006401322002020039200399977699908012020080032200801432003920039118020110099100100800001000101115118011611200360800001002004020040200402004020040
8020420039155101030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118011611200360800001002004020040200402004020040
80204200391561010410258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118011611200360800001002004020040200402004020040
80204200391551010302580108100800081008002050064013220020200392003999776100078012020080032200800322003920039118020110099100100800001000001115118011611200360800001002019220040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b181e1f3f51inst 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)5f60696b6d6edispatch 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)9fa1a8accficache miss (d3)d5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420099155000040258001010800001080000506400000020020020039200399996031001980010208000020800002003920039118002110910108000010003502004163320036080000102004020040200402004020040
80024200391550000402580010108000010800005064000001200200200392003999960310019800102080000208000020039200391180021109101080000100012502003163320036080000102004020040200402004020040
80024200391560000402580010108000010800005064000001200200200392003999960310019800102080000208000020039200391180021109101080000100012502003163320036080000102004020040200402004020040
8002420039156000040258001010800001080000506400000120020020039200399996031001980010208000020800002003920039118002110910108000010020502003163420036080000102004020040200402004020040
8002420039155010040258001010800001080000506400000120020020039200399996031001980010208000020800002003920039118002110910108000010020502004164320036080000102004020040200402004020040
8002420039155000040258001010800001080000506400000020020020039200399996031001980010208000020800002003920039118002110910108000010000502004164320036080000102004020040200402004020040
80024200391550000230258001010800001080000506400000020020020039200399996031001980010208000020800002003920039118002110910108000010000502003163320036080000102004020040200402004020040
8002420039155000040258001010800001080000506400000120020020039200399996031001980010208000020800002003920039118002110910108000010000502004164420036080000102004020040200402004020040
8002420039156000040258001010800001080000506400000120020020039200399996031001980010208000020800002003920039118002110910108000010060502003164320036080000102004020040200402004020141
8002420039155000040258001010800001080000506400000120020020039200399996031001980010208000020800002003920039118002110910108000010000502004165320036080000102004020040200402004020040