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, 8H)

Test 1: uops

Code:

  srshr v0.8h, 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)03093f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073316112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722020825472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372206125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
100430372216125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  srshr v0.8h, 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)031e3f4e51inst 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)696b6d6edispatch 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
102043003722506129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722506129547251010010010000104100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300180300373003728264328745101002001000020410000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722406129547251010010010000100100005004277160300180300843003728264328745102772001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225069029547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500006129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160300183003730037283043287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000010629547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229667010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037224000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000130006402162229629010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500036129547251001010100001010000504277160300183008430037282863287671001020100002010000300373003711100221091010100001000000306402242229629010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  srshr v0.8h, v8.8h, #3
  srshr v1.8h, v8.8h, #3
  srshr v2.8h, v8.8h, #3
  srshr v3.8h, v8.8h, #3
  srshr v4.8h, v8.8h, #3
  srshr v5.8h, v8.8h, #3
  srshr v6.8h, v8.8h, #3
  srshr v7.8h, 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)030708090a18191e1f3f51inst 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)9fa1a6a7a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059150100100570410258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511811611200360800001002004020040200402004020040
802042003915010010054030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511811611200360800001002004020040200402004020040
80204200391501001000030258010810080108100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511811611200360800001002004020040200402004020040
80204200391501001000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511811611200360800001002004020040200402004020040
8020420039150100100522030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511811611200360800001002004020040200402004020040
8020420039150100100489030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511811611200360800001002004020040200402004020040
802042003915010010057030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511811611200360800001002004020040200402004020040
80204200391501001000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511811611200360800001002004020040200402004020040
802042003915010010045030258010810080008100800205006401321200202003920039997769990801202008013620080032200392003911802011009910010080000100000000111511811611200360800001002004020040200402004020040
802042003915010010030030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511811611200360800001002004020040200402004020040

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)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)9fa8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020161611182003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000305020181614182003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000502015169182003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020201618182003680000102004020040200402004020040
800242003915104025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020181618112003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020151618152003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020151618152003680000102004020040200402004020040
800242003915006125800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020131619172003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020171616182003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020151618112003680000102004020040200402004020040