Apple M1 Microarchitecture Research by Dougall Johnson

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

URSHL (vector, 8B)

Test 1: uops

Code:

  urshl v0.8b, v0.8b, v1.8b
  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)031e3f4e51inst 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
10043037221866125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723276125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723276125392510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303722017925482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  urshl v0.8b, v0.8b, v1.8b
  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)03191e3f4e51inst 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)91inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa6a8c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250574412954825101001001000010010000500427731303001830037300372827262874110100200100082002036230085300371110201100990100100100001002311171701600296460100001003003830038300383003830038
1020430037225030612954825101001001000010010000500427731303001830037300372827272874010100200100082002001630037300371110201100990100100100001000000071011611296343100001003003830038300383003830038
1020430037225045612954825101001001000010010000542427731303001830037300372826532874510100200100002002000030037300371110201100990100100100001000000071011611296340100001003003830038300383003830038
1020430037224033612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100990100100100001000000071011611296340100001003003830038300383003830038
10204300372250655472954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100990100100100001000000071011611297060100001003003830038300383003830038
10204300372241270842954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100990100100100001000000071011611296340100001003003830038300383003830038
1020430037225045612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100990100100100001000000071011611296340100001003003830038300383003830038
1020430037225066129548251010010010000100100005004277313030018300373003728265102874510100200100002002000030037300371110201100990100100100001000000071011611296340100001003003830038300383003830038
1020430037225057612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100990100100100001000000071011611296340100001003003830038300383003830038
1020430037225018612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100990100100100001000000071011611296340100001003003830038300383003830038

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 branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500004770612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000822954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300782250000690612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500004170612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500004050612954825100101010000101000050427731313001830037300852828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500004170612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500003960612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162230034010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  urshl v0.8b, v1.8b, v0.8b
  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)03091e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300882250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000062642773130300183003730037282653287451010020010000200200003003730037111020110099100100100001001371011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002022000030037300371110201100991001001000010000710116112963425100001003003830038300383003830077
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071211611296340100001003003830038300383003830038
10204300372250061295482510100100100071001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b18191e3f4e51inst 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)9fa0a6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500023761295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000640416442963010000103003830038300383003830038
1002430037225030061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000640316442963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000640416442963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000640416432963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000640316442963010000103003830038300383003830038
1002430037225000661295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000640416442963010000103003830038300383003830038
10024300372250002161295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000640416442963010000103003830038300383003830038
10024300372250005461295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000640416442963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000640416432963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000640416442963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  urshl v0.8b, v8.8b, v9.8b
  urshl v1.8b, v8.8b, v9.8b
  urshl v2.8b, v8.8b, v9.8b
  urshl v3.8b, v8.8b, v9.8b
  urshl v4.8b, v8.8b, v9.8b
  urshl v5.8b, v8.8b, v9.8b
  urshl v6.8b, v8.8b, v9.8b
  urshl v7.8b, v8.8b, v9.8b
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03080b18191e1f3f51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003915000001503025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000002000111511801600200360800001002004020040200402004020040
80204200391500000004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000000511011611200360800001002004020040200402004020040
80204200391500000004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000000000511011611200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000201710000511011611200360800001002004020040200402004020040
80204200391500000004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000000511011611200360800001002004020040200402004020040
802042003915000000070625801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000004000000511011611200360800001002004020040200402004020040
80204200391500000004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000000511011611200360800001002004020040200402004020040
80204200391500000004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000001000000511011611200360800001002004020040200402004020040
80204200391500000004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000007000000511011611200360800001002004020040200402004020040
802042003915000000070625801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000000511011611200360800001002004020040200402004020040

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)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)9fa6a7a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915004025800101080000108000050640000020020020039200399996310019800102080000201600002003920039118002110910108000010000005020316232003680000102004020040200402004020040
800242003915005025800101080000108000050640000120020020039200399996310019800102080000201600002003920039118002110910108000010000005020316322003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020020039200399996310019800102080000201600002003920039118002110910108000010002005020216232003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200200200392003999963100198001020800002016000020039200391180021109101080000100010005020316322003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020020039200399996310019800102080000201600002003920039118002110910108000010004005020316322003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020020039200399996310019800102080000201600002003920039118002110910108000010000005020316422003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020020039200399996310019800102080000201600002003920039118002110910108000010000005020316332003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020020039200399996310019800102080000201600002003920039118002110910108000010001305020316322003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020020039200399996310019800102080000201600002003920039118002110910108000010200305020316322003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020020039200399996310019800102080000201600002003920039118002110910108000010000005020316232003680000102004020040200402004020040