Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRSHRUN (8H)

Test 1: uops

Code:

  sqrshrun v0.8b, v0.8h, #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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037239061254725100010001000398160130183037303724143289510001000100030373037111001100001573116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372308225472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqrshrun v0.8b, v0.8h, #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)03181e3f4e51inst 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
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037224006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250044129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372240053629547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100037101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
1002430037224000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229701010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqrshrun v0.8b, v8.8h, #3
  sqrshrun v1.8b, v8.8h, #3
  sqrshrun v2.8b, v8.8h, #3
  sqrshrun v3.8b, v8.8h, #3
  sqrshrun v4.8b, v8.8h, #3
  sqrshrun v5.8b, v8.8h, #3
  sqrshrun v6.8b, v8.8h, #3
  sqrshrun v7.8b, v8.8h, #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)030708090a0b18191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000000002400302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160200360800001002004020040200402004020040
802042003915000000001500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160200360800001002004020040200402004020040
802042003915000000001200302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160200360800001002004020040200402004020040
80204200391500000000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160200360800001002004020040200402004020040
80204200391500000000150011092580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160200360800001002004020040200402004020040
80204200391500000000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160200360800001002004020040200402004020040
80204200391500000000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160200360800001002004020040200402004020040
802042003915000000000001252580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160200360800001002004020040200402004020040
80204200391500000000900302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000003011151180160200360800001002004020040200402004020040
802042003915000000003900302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160200360800001002004020040200402004020040

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)5f60696d6edispatch 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001021646850209168620036080000102004020040200402004020040
800242003915000402580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010010188250208166820036080000102004020040200402004020040
800242003915000402580010108000010800005064000001200202003920039999631001980122208000020800002003920039118002110910108000010000050207167520036180000102004020040200402004020040
800242003915000822580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050208165720036080000102004020040200402004020040
80024200391502940402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010040350207166720036080000102004020040200402004020040
800242003915000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050207167520036080000102004020040200402004020040
800242003915000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050208168620036080000102004020040200402004020040
800242003915000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010010050205166820036080000102004020040200402004020040
800242003915000402580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010000050208167720036080000102004020040200402004020040
8002420039150300402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050207168620036080000102004020040200402004020040