Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRSHRN (2D)

Test 1: uops

Code:

  sqrshrn v0.2s, v0.2d, #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)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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723082254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100001073116112629100030383038303830383038
10043037230170254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100001073116112629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqrshrn v0.2s, v0.2d, #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)0308090b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000055529547451012412710032100100005004277160130018300373003728264032874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383003830038
10204300372320000000021229547251010010010000100100005004277160130018300373003728264032874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383003830038
10204300372250000000019329547251010010010000100100005004277160130018300373003728264032874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383003830038
10204300372250000000021429547251010010010000100100005004277160130018300373003728264032874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383003830086
10204300372320000000011729547251010010010000100100005004277160030018300373003728264032874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383003830038
102043003722500000300012429547251010010010000100100005004277160130018300373003728264032874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383003830038
10204300372250000000016629547251010010010000100100005004277160130018300373003728264032874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383003830038
10204300372250000000012429547251010010010000100100005004277160130018300373003728264032874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383003830038
10204300372250000000018929547251010010010000100100005004277160130018300373003728264032874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383008630038
10204300372250000000012429547251010010010000100100005004277160130018300373003728264032874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b191e1f3f4e51inst 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)60696b6d6edispatch 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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000017229547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010040000640216222962910000103003830038300383003830038
1002430037225000016829547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
1002430037225000021229547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722400008229547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
1002430037225000019329547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
1002430037225000017229547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
1002430037241000017229547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000090640216222962910000103003830038300383003830038
1002430037225000019129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300853003830038
1002430037225000019129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
1002430037237000047429547251001010100001010000504279387030018030084300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqrshrn v0.2s, v8.2d, #3
  sqrshrn v1.2s, v8.2d, #3
  sqrshrn v2.2s, v8.2d, #3
  sqrshrn v3.2s, v8.2d, #3
  sqrshrn v4.2s, v8.2d, #3
  sqrshrn v5.2s, v8.2d, #3
  sqrshrn v6.2s, v8.2d, #3
  sqrshrn v7.2s, v8.2d, #3
  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)0308193f51inst 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)9facc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200671500097258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151181160020036800001002004020040200402004020040
802042003915501220258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
80204200391500058258010810080008100800205006407880200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100611151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

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)9fa0a8accfd2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500010925800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001001405020004160004220036080000102004020040200402004020040
80024200391500429402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100035020004160004420036080000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100065020002160004220036080000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020004160004420036080000102004020040200402004020040
800242003915000705258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010004755020002160002420036080000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020004160004220036080000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020004160003420036080000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020002160004420036080000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020003160004220036080000102004020040200402004020040
800242003915000612580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020002160004220036080000102009220092200402004020094