Apple M1 Microarchitecture Research by Dougall Johnson

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

SQABS (scalar, S)

Test 1: uops

Code:

  sqabs s0, s0
  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)031e1f3f4e51inst 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
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303722006125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037220010325472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303722006125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037220010525472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037230014725472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037230010325472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037230010325472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqabs s0, s0
  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)0308183f4e51inst 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037224006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282643287451010020010000216100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372250053629547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372250037029547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)6061696b6d6edispatch 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)9fa0a1a8a9acc2cfd0d5d6daddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300852251000015061295472510010101000010100005042771600030018030037300372828632876710010201000020100003003730037111002110910101000010000000640031602229629010000103003830038300383003830038
1002430037224000000061295472510010101000010100005042771600030018030037300372828632876710010201000020100003003730037111002110910101000010000000640021602229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600030018030037300372828632876710010201000020100003003730037111002110910101000010000000640021602229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600030018030037300372828632876710010201000020100003003730037111002110910101000010000000640021602229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600030018030037300372828632876710010201000020100003003730037511002110910101000010000000640021602229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600030018030037300372828632876710010201000020100003003730037111002110910101000010000000640021602229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600030018030037300372828632876710010201000020100003003730037111002110910101000010000000640021602229629010000103003830038300383003830038
1002430037225000000082295472510010101000010100005042771600030018030037300372828632876710010201000020100003003730037111002110910101000010000000640021602229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600030018030037300372828632876710010201000020100003003730037111002110910101000010000000640021602229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600030018030037300372828632876710010201000020101083003730037111002110910101000010000000640021602229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqabs s0, s8
  sqabs s1, s8
  sqabs s2, s8
  sqabs s3, s8
  sqabs s4, s8
  sqabs s5, s8
  sqabs s6, s8
  sqabs s7, s8
  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)0308090b18191e1f3f51inst 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)9fa0a1a6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006115000000003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
8020420039150000002403025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
80204200391500000027303025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511804100200360800001002004020040200402004020040
802042003915000000003025801081008000810080020511644970200202003920039997769990801202008003220080032200392003911802011009910010080000100000200111511801600200360800001002004020040200402004020040
802042003915000000603025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040

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)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)9fa8accfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401500402580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010005020516151520036080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001000502031651520036080000102004020040200402004020040
800242003915006142580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010005020131615620036080000102004020040200402004020040
8002420039150061258001010800001080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001000502031661620036080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001000502051661620036080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001000502051616620036080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001000502071661620036080000102009120040200402004020040
800242003918607282580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010005020141615520036080000102004020040200402004020040
80024200391500402580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010047650201516161620036080000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000100050201516151520036080000102004020040200402004020040