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, 2D from 2D)

Test 1: uops

Code:

  ucvtf v0.2d, v0.2d
  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)696d6edispatch 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)e0? fp/simd (ee)f5f6f7f8fd
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110003073116112701100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110001373116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000973116112629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240612547251000100010003996773018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000673116112629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000673116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  ucvtf v0.2d, v0.2d
  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)031e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723309929547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372321276829547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723336129547621010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723308929547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100107101161129633100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa1a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000411295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
1002430084225000000082295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
10024300372250000000103295472510010101000010100005042771600300183003730037282866287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
1002430037224000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
1002430037224000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
100243003722500000002128295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
100243003722500000001415295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006613163329629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  ucvtf v0.2d, v8.2d
  ucvtf v1.2d, v8.2d
  ucvtf v2.2d, v8.2d
  ucvtf v3.2d, v8.2d
  ucvtf v4.2d, v8.2d
  ucvtf v5.2d, v8.2d
  ucvtf v6.2d, v8.2d
  ucvtf v7.2d, v8.2d
  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)031e1f3f51inst 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)9fa0a6a7a8a9abacc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042004915512030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151183163420036800001002004020040200402004020040
80204200391550030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000300000011151183162320036800001002004020040200402004020040
80204200391550030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151183163420036800001002004020040200402004020040
80204200391550030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151183164420036800001002004020040200402004020040
80204200391550030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151183163320036800001002009020040200402004020040
80204200391550030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151184164420036800001002004020040200402004020040
80204200391610030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151182164320036800001002004020040200402004020040
8020420039155297030258010810280008100800205006401322002020039200399977699908023220080032200800322003920039118020110099100100800001000000000011151183164420036800001002004020040200402004020040
80204200391550030258010810080008100801265006401322002020039200399995699908012020080032200800322003920039118020110099100100800001000003000011151183164320036800001002004020040200402004020040
80204200391550080258010810080008100800205006401322014020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151183163320036800001002004020040200402004020040

1000 unrolls and 10 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)5f696d6edispatch 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)9fa0a1a8acb5cfd0d2icache miss (d3)d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501550822580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000050200103163220036080000102004020040200402004020040
80024200391550402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000050200003162320036080000102004020040200402004020040
80024200391550405080010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100200050200003163220036080000102004020040200402004020040
80024200391560402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000050200003163220036080000102004020040200402004020040
800242003915502752580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000050200003163220036080000102004020040200402004020040
80024200391550402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000050200003163320036080000102004020040200402004020040
80024200391550402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100009050200003163220036080000102004020040200402004020040
80024200391550402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000050200003162320036080000102004020040200402004020040
80024200391560452580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000050200002163320036080000102004020040200402004020040
80024200391550402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100100050200003163320036080000102004020040200402004020040