Apple M1 Microarchitecture Research by Dougall Johnson

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

SQNEG (scalar, D)

Test 1: uops

Code:

  sqneg d0, d0
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303722010325472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372413328951000100010003037303711100110000073116222629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000075216112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110003373116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723010525472510001000100039816003018303730372413328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqneg d0, d0
  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)0308090b191e1f3a3f4e51inst 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)9fa6a8acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000006129547251010010010000100100005004277160130018300373003728264328820101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
1020430037225100012006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722500000006129547621010010010000100100005004277160130018300373003728264328745101002001000020010000302303003711102011009910010010000100003007101161129633100001003003830038300383003830038
102043003722500001448806129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100003007101161129633100001003022730038300383003830038
102043003722500009006129547251010010010000100100005004277160130018300373003728264328745101002141000020010000300373003711102011009910010010000100000007102161129779100001003003830038300383003830038
102043003722500000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722500000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722500000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373013411102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722500100006129547251010010010032100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000017101161129633100001003018230038300383003830038
102043003722500000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080a0b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000064041633296290010000103003830038300383003830038
1002430037225000000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000064031633296290010000103003830038300383003830038
10024300372250000000053629547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000064041633296290010000103003830038300383003830038
100243003722400000000330329493801002013100481110900604282568030018300373003728286328767100102010000201000030037300371110021109101010000100000000064031633296290010000103003830038300383003830038
1002430037225100000006129538251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000064031633296290010000103003830038300853003830038
10024300372250001013252806129547251001010100001010000604277160130306303213003728302202882310010201016122106493036830368111002110910101000010423101382620813890512300243010000103055830558305603055630558
1002430369236001612145270407223294572461011119100882011650984293384030018300373022828298328767100102010000201032930561305601111002110910101000010400021669520709966410298323010000103036930038300383003830038
10024300372250004053417611812944825101041510088141165082428797603045030558304612831454289551091322117932210627305583059413110021109101010000102000233590208968901313299533010000103036830417305583068130414
10024303712360000000041929547611001011100161310000504277160030018301323003728286328767100102610000201000030179305021110022109101010000100000030164031633296290010000103003830038300383003830038
1002430037224001000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000064031633296290010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqneg d0, d8
  sqneg d1, d8
  sqneg d2, d8
  sqneg d3, d8
  sqneg d4, d8
  sqneg d5, d8
  sqneg d6, d8
  sqneg d7, d8
  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)03070a18191e3f51inst 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)9fa8c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061150000009202580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000111511811611200360800001002004020040200402004020040
802042003915011000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000111511811611200360800001002004020040200402004020040
802042003915011000302580108100800081008002050064013202002020039201139986699908012020080032200800322003920039118020110099100100800001000111511811611200360800001002004020040200402004020040
802042003915001000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000111511811610200360800001002004020040200402004020040
802042003915011000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000111511811611200360800001002004020040200402004020040
802042003915011000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000111511811611200360800001002004020040200402004020040
802042003915011000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000111511811612200360800001002004020040200402004020040
802042003915011000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000111511811611200360800001002004020040200402004020040
802042003915011000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000111511811611200360800001002004020040200402004020040
802042003915011000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000111511811611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030809181e3f51inst 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)5f6061696d6edispatch 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)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000004025800101080000108000050640000000200202003920039999631001980010208000020800002009020090118002110910108000010019015020001816111220036080000102004020040200402004020040
800242003915000004025800101080000108010350640000010200202003920039999631001980010208000020800002003920039118002110910108000010005020541216121120036080000102004020040200402004020040
800242003915000004025800101080000108000050640000005200202003920039999631001980010208000020800002003920039118002110910108000010005020501016111220036080000102004020040200402004020040
800242003915000004025800101080000108000050640000015200202003920039999631001980010208000020800002003920039118002110910108000010005020501316131520036080000102004020040200402004020040
800242003915000004025800101080000108000050640000005200202003920039999631001980010208000020800002003920039118002110910108000010005020501116131520036080000102004020040200402004020040
800242003915000404025800101080000108000050640000005200202003920039999631001980010208000020800002003920039118002110910108000010005020501116121320036080000102004020040200402004020040
800242003915000004046800101080000108000050640000015200202003920039999631001980010208000020800002003920039118002110910108000010005020041216121120036080000102004020040200402004020040
800242003915000004025800101080000108000050640000010200202003920039999631001980010208000020800002003920039118002110910108000010005020541216131220036080000102004020040200402004020040
800242003915000004025800101080000108000050640000000200202003920039999631001980010208000020800002003920039118002110910108000010005020501216111120036080000102004020040200402004020040
800242003915000004025800101080000108000050640000015200202003920039999631001980010208000020800002003920039118002110910108000010005020501116111120036080000102004020040200402004020040