Apple M1 Microarchitecture Research by Dougall Johnson

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

UCVTF (scalar, integer, H from H)

Test 1: uops

Code:

  ucvtf h0, h0
  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)0308090b18191e1f3f4e51inst 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)a0a1a7a8a9acc2cfd5d6d9ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300000006125472510001000100039816013018303730372414728981150100011633084307321100110000000028462941240112645100030383038308630743085
10043084241001014488100225384410081008115039951203054308430852418629071000116211613084308421100110000011204741731400112664100030853038308430863038
1004308524101119888032547441008100811503995120301830843085241482914115011621000308530372110011000220422234931240112645100030863084308530863085
1004308423000011328875025384910001008110739951213018303730372414328951000100010003037303711100110000003000731160112629100030383038303830383038
1004303724001000010425472510001000100039816013018303730372414328951000100010003037303711100110002203039900911240112658100030863074308630853086
10043037251011113288134725472510081000115039951213090303730842422829141139100010963084308421100110000003453952941240112724100031203121312231213122
1004316825011112641768992538431008101311503981600305431673083241810291411501162116830833083211001100000000407521001240112674100030863131312130853084
10043132251001113217661254725100010001000398160030183037303724143289510001000100030373037111001100000118228600731160112629100030383038303830383038
10043037240000060926253844101610001000398160130183037303724143289510001000100030373037111001100000070720731160112629100030383038303830383038
10043037240000000612547251000100010003981601301830373037241432895100010001000303730371110011000200222200731160112629100030383038313231323133

Test 2: Latency 1->2

Code:

  ucvtf h0, h0
  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)6063696d6edispatch 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300280295472510100100100001001000050042771601030018300373003728264328745101002001000020010000300373003711102011009910010010000100007102161129633100001003008530038300383003830038
10204300372320061295472510100114100081131015050042771601030018300373003728264328745101002001000020010000300373003711102011009910010010000100037101161129633100001003008730038300383003830038
10204300372412768861295472510100100100001001000050042771601030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101241129633100001003003830038300383003830038
102043003723312061295472510100100100001001000050042771601030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723312061295472510100100100001001000050042771601030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723300210295472510130100100001341000052242771601030018300373003728264328745101002001033320010498300373003711102011009910010010000100037101161129633100001003003830038300383003830038
10204300372330061295472510100100100001001000050042771601030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723300202295472510100100100001001000050042771601030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723327061295472510100100100001001000050042771601030018300373023228264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372330061295472510100100100001001000050042771601030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)033f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372331092954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100006403163329629010000103003830038300383003830038
10024300372337262954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100326403163329629010000103003830038300383003830038
1002430037233612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100006403163329629010000103003830038300383003830038
1002430037233612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100006403163329629010000103003830038300383003830038
1002430037232612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100006403163329629010000103008630038300383003830038
1002430084233612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100006403163329629010000103003830038300383003830038
1002430037233612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100006403163329629010000103003830038300383003830038
1002430037233612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100006403163329629010000103003830038300383003830038
1002430037232612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100006403163329629010000103003830038300383003830038
1002430037232612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100006403163329629010000103003830038302283003830038

Test 3: throughput

Count: 8

Code:

  ucvtf h0, h8
  ucvtf h1, h8
  ucvtf h2, h8
  ucvtf h3, h8
  ucvtf h4, h8
  ucvtf h5, h8
  ucvtf h6, h8
  ucvtf h7, h8
  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)030b1e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420049155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010003111511831600200360800001002004020040200402004020040
802042003915500106025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010009111511801600200360800001002004020040200402004020040
8020420039155003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200362800001002004020040200402004020040
80204200391550015825801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
8020420039161007225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
80204200391550014625801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
8020420039156007225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200361800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801610200360800001002004020040200402004020040
80204200391560011625801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115500125258001010800001080000506400001200202003920039999603100198001020800002080000200392003911800211091010800001000050201716181820036080000102004020040200402004020040
80024200391550056258001010800001080000506400001200202003920039999603100198001020800002080000200392003911800211091010800001000050201816181820036080000102004020040200402004020040
80024200391550025942801081080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000100005020181691820036080000102004020040200402004020040
8002420039156007325800101080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000100005020181615720036080000102004020040200402004020040
800242003916100682580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010000502091618920036080000102004020040200402004020040
800242003915500692580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010000502091691820036080000102004020040200402004020040
800242003915500682580010108000010800005064000012002020039200399996031001980010208000020800002003920039118002110910108000010000502091618920036080000102009120040200402004020040
80024200391560010902580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010000502091618920036080000102004020040200402004020040
800242003915500682580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010000502071681820036080000102004020040200402004020040
800242003915600892580010108000010800005064000012002020039200399996031001980010208000020800002003920039118002110910108000010000502071618720036080000102004020040200402004020040