Apple M1 Microarchitecture Research by Dougall Johnson

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

SRSHR (vector, 2D)

Test 1: uops

Code:

  srshr v0.2d, 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)03181e3f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230061254725100010001000398160130183037303724143289510001000100030373037111001100010373116112629100030383038303830383038
10043037220361254725100010001000398160030183037303724143289510001000100030373037111001100012073116112629100030383038303830383038
100430372300126254725100010001000398160030183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061253825100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037231061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160130183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
10043037220061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160130183037303724143289510001000100030373037111001100000673116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  srshr v0.2d, 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)03191e1f3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000441295472510100100100001001000050042771600300180300373003728264328745102502001000020010000300373003711102011009910010010000100107101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100407101161129633100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001005507101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100107101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100397101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100067101161129633100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001001007101161129633100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001001007101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100107101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03090b18191e1f3f4e51inst 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)6061696d6edispatch 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)9fa0a1a6a7a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000612954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001000000033006402162229629010000103003830038300383003830038
10024300372250000006129547251001810100001010000504277160003001830037300372828632876710010201000020100003003730037111002110910101000010000000135006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600030018300373003728286328767100102010000201000030037300371110021109101010000100000103006402162229629210000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600030018300373003728286328767100102010000201000030037300371110021109101010000100000103006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600030018300373003728286328767100102010000201000030037300371110021109101010000100000200006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600030018300373003728286328767100102010000201000030037300371110021109101010000100000103006402162229629010000103003830038300383003830038
100243003722400000061295472510010101000010100005042771600030018300373003728286328767100102010000201000030037300371110021109101010000100000103006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600030018300373003728286328767100102010000201000030037300371110021109101010000100000203006402162229629010000103003830038300383003830038
100243003722400000061295472510010101000010100005042771600030018300373003728286328767100102010000201000030037300371110021109101010000100000006006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600030018300373003728286328767100102010000201000030037300371110021109101010000100000203006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  srshr v0.2d, v8.2d, #3
  srshr v1.2d, v8.2d, #3
  srshr v2.2d, v8.2d, #3
  srshr v3.2d, v8.2d, #3
  srshr v4.2d, v8.2d, #3
  srshr v5.2d, v8.2d, #3
  srshr v6.2d, v8.2d, #3
  srshr v7.2d, 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)030818191e1f3f51inst 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)9fa0a6a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003915000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
802042003915000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
802042003915000030402580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
802042003915000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000010311151180160020036800001002004020040200402004020040
802042003915000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
802042003915000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
802042003915000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000311151180160020036800001002004020040200402004020040
8020420039151000003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000210011151180160020036800001002004020040200402004020040
802042003915000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000010011151180160020036800001002004020040200402004020040
802042003915000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3f51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100035020116112003680000102004020040200402004020040
800242003915010402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180022109101080000100035020116112003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100235020116112003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020116112003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100035020116112003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020116112003680000102004020040200402004020093
800242003915200402580010108000010800005064000002002020039200399996310019800102080000208000020039200912180021109101080000100065020216112003680000102004020040200402004020040
8002420039150012135258001010800001080000506400000200202003920039999631001980010208010620800002003920039118002110910108000010004865020116112003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020116112003680000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001002105020116112003680000102004020040200402004020040