Apple M1 Microarchitecture Research by Dougall Johnson

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

FMINV (4H)

Test 1: uops

Code:

  fminv h0, 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)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)a0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220822547251000100010003981600301830373037241432895100010001000303730371110011000000973116112629100030383038303830383038
10043037230612547251000100010003981601301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
10043037230612547251000100010003981601301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
100430372318612547251000100010003981600301830373037241432895100010001000303730371110011000008073116112629100030383038303830383038
10043037220612547251000100010003981600301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
10043037230612547251000100010003981600301830373037241432895100010001000303730371110011000000373116112629100030383038303830383038
10043037230612547251000100010003981600301830373037241432895100010001000303730371110011000002073116112629100030383038303830383038
10043037230612547251000100010003981601301830373037241432895100010001000303730371110011000001073116112629100030383038303830383038
10043037230612547251000100010003981600301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
100430372301052547251000100010003981600301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fminv h0, 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)0308181e3f4e51inst 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)9fa1a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225005946129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007102161129633100001003003830038300383003830038
10204300372250006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037224004146129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225002436129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225004836129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129704100001003003830038300383003830038
1020430037225003396129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225004476129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100107101161029633100001003003830038300383003830038
1020430037225004296129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100107101161129633100001003003830038300383003830038

1000 unrolls and 10 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
100243003722553182295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722512361295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722427061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722535461295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722518061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722540561295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372249661295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640216122962910000103003830038300383003830038
100243003722541461295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
1002430037225360536295472510010101000010101485042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722538461295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001020640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fminv h0, v8.4h
  fminv h1, v8.4h
  fminv h2, v8.4h
  fminv h3, v8.4h
  fminv h4, v8.4h
  fminv h5, v8.4h
  fminv h6, v8.4h
  fminv h7, 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)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)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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915112302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151182163320036800001002004020040200402004020040
80204200391509302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151183164320036800001002004020040200402004020040
802042003915015302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151183164420036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151184162420036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151183164320036800001002004020040200402004020040
80204200391501839202580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151184164320036800001002004020040200402004020040
802042003915001352580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151183163220036800001002004020040200402004020040
80204200391509302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151182164320036800001002004020040200402004020040
80204200391500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151184164320036800001002004020040200402004020040
802042003915015302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151183164420036800001002004020040200402004020040

1000 unrolls and 10 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)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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915024040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000050203162320036080000102004020040200402004020040
800242003915000515258001010800001080000506400001200202003920039999631001980010208000020800002007520039118002110910108000010000050203163320036080000102004020040200402004020040
80024200391500040258001010800001080000506400001200702003920039999631001980010208000020800002003920039118002110910108000010000050203163320036080000102004020040200402004020040
80024200391509040258001010800991080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000050202162320036080000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000050203163320036080000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000050203163320036080000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000050203163320036080000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000050203162320036080000102004020040200402004020040
800242003915012040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010400050203162320036080000102004020040200402004020040
800242003915021040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000050203162320036080000102004020040200402004020040