Apple M1 Microarchitecture Research by Dougall Johnson

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

RSHRN (4S)

Test 1: uops

Code:

  rshrn v0.4h, v0.4s, #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)03191e3f4e51inst 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
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
1004303723007425472510001000100039816013018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
1004303722006125472510001000100039816013018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
1004303723008225472510001000100039816013018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
1004303722006125472510001000100039816013018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
1004303723008225472510001000100039816013018303730372414328951000100010003037303711100110000073316332629100030383038303830383084
1004303723036125472510001000100039816013018303730372414328951000100010003037303711100110001373316332629100030383038303830383038

Test 2: Latency 1->2

Code:

  rshrn v0.4h, v0.4s, #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)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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225010329547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830086
102043003723606129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001003007102162229633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
1020430037224011029547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
1020430037225156129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
1020430037225021629547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
102043003722506129547251010010010000100101485004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038

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)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)9fa0a1a6a7a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224000000612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
10024300372240000198108612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
10024300372250000007262954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162629629010000103003830038300383003830038
10024300372250000002512954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
10025300372250000007262954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
10024300372240000003382954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  rshrn v0.4h, v8.4s, #3
  rshrn v1.4h, v8.4s, #3
  rshrn v2.4h, v8.4s, #3
  rshrn v3.4h, v8.4s, #3
  rshrn v4.4h, v8.4s, #3
  rshrn v5.4h, v8.4s, #3
  rshrn v6.4h, v8.4s, #3
  rshrn v7.4h, v8.4s, #3
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

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)9fa8c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581511830258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
8020420039150330258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
8020420039150630258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020116
8020420039150030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
802042003915044130258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
8020420039150930258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200912004020040
802042003915028230258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151181160020036800001002004020040200402004020040
8020420039150030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
8020420039150030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
802042003915042930258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020040

1000 unrolls and 10 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500003906125800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000012905020116112003680000102004020040200402004020040
80024200391500000040508001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
80024200391500000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
8002420039150000510230258001010800001080000506400000200202003920039999631012480010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
800242003915000024040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
80024200391500000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020116172003680000102004020040200402004020040
8002420039150000120214258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
800242003915000030040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
80024200391500009040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
80024200391500000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040