Apple M1 Microarchitecture Research by Dougall Johnson

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

URSHR (vector, D)

Test 1: uops

Code:

  urshr d0, d0, #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)030a1e3f4e51inst 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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303722106625472510001000100039816030183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303723006125472510001000100039816030183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303723106125472510001000100039816030183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303722066125472510001000100039816030183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303723106125472510001000100039816030183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303723106125472510001000100039816030183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303723066125472510001000100039816030183037303724143289510001000100030373037111001100073116112629100030383038303830383038
10043037231876125472510001000100039816030183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303723106125472510001000100039816030183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303723106125472510001000100039816030183037303724143289510001000100030373037111001100073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  urshr d0, d0, #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)033f4e51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722561295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003722561295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383008230038
102043003722561295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003722561295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003722561295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003722561295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000971011611296330100001003003830038300383003830038
102043003722561295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100001071011611296330100001003003830038300383003830038
102043003722561295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003722561295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003722561295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038

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 function returns (8f)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000007129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021100910101000010000000006404164429629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021100910101000010000000006404164429629010000103003830038300383003830038
1002430037225000001326129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021100910101000010000000006404164329629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021100910101000010000000006403164429629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021100910101000010000000006403163429629010000103003830038300383003830038
10024300372240000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021100910101000010000000006403164429629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021100910101000010000000006404164329629010000103003830038300383003830038
100243003722500001806129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021100910101000010000000006403164329629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021100910101000010000000006404164329629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021100910101000010000000006404164329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  urshr d0, d8, #3
  urshr d1, d8, #3
  urshr d2, d8, #3
  urshr d3, d8, #3
  urshr d4, d8, #3
  urshr d5, d8, #3
  urshr d6, d8, #3
  urshr d7, d8, #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)0318191e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000074258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
8020420039150000139258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
8020420039150000206258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
80204200391500001019258010810080008100800205006401321200203200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
8020420039150000478258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
8020420039150000283258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
8020420039150000116258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010010111511801620036800001002004020040200402004020040
8020420039150000116258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
802042003915000074258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
802042003915000030258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040

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)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)9fa0a1a6a8a9accfd0d2icache miss (d3)d5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115004525800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020000171601362003680000102004020040200402004020040
80024200391500402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000000502000061606132003680000102004020040200402004020040
800242003915004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020310161601662003680000102004020040200402004020040
800242003915004025800101080000108000050640000002002020039200399996310019800102080000208014020039200391180021109101080000105001065020000161606162003680000102004020040200402004020040
80024201141500402580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010000000502000061606162003680000102004020040200402004020040
800242003915004025800101080000108000050640000112002020039200399996310019800102080000208000020039200391180021109101080000100000005020000161601662003680000102004020040200402004020040
800242003915004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020000161606162003680000102004020040200402004020040
800242003915004025800901080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020000161601662003680000102004020040200402004020040
800242003915004025800101080000108000050640000112002020039200399996310019800102080000208000020039200391180021109101080000100203005020000131606162003680000102004020040200402004020040
800242003915104025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100100005020000121601662003680000102004020040200402004020040