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, D)

Test 1: uops

Code:

  urshl d0, d0, d1
  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
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372208225482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
1004303723010325482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
1004303722126125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038

Test 2: Latency 1->2

Code:

  urshl d0, d0, d1
  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)0318191e1f3f4e51inst 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)9fa8a9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500528061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010040007102162229634100001003003830038300383003830038
10204300372250039061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
1020430037225009061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
10204300372250038704804295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722500372061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722500402061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
1020430037225004020103295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722500387061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
10204300372250043501065295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722500429061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030708090a0b18191e1f3f4e51inst 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
1002430037225000000059706129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006407166629630010000103003830038300383003830038
1002430037225000000022806129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006406166629630010000103003830038300383003830038
1002430037225000000050706129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006406166629630010000103003830038300383003830038
1002430037225000000046506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006405166729630010000103003830038300383003830038
10024300372250000000006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006407167729630010000103003830038300383003830038
10024300372250000000006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006406167629630010000103003830038300383003830038
10024300372250000000492010329548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006405166729630010000103003830038300383003830038
10024300372250000000306129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006406166629630010000103003830038300383003830038
10024300372250000000462023229548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006406167629630010000103003830038300383003830038
1002430037225000000042906129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006407167629630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  urshl d0, d1, d0
  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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722502106129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722503906129548251010010010000100100005004277313030018030037300372826532874510100200103322002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250606129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722501506129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722501806129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300842110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250608229548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250606129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722506306129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000000471011611296340100001003003830038300383003830038
10204300372250300129429548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa8c3cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225264061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250082295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722545061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722512061295482510010101000010100005042786703001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722445061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372256061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372256061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722527061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722521061295482510010101000810100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722536061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  urshl d0, d8, d9
  urshl d1, d8, d9
  urshl d2, d8, d9
  urshl d3, d8, d9
  urshl d4, d8, d9
  urshl d5, d8, d9
  urshl d6, d8, d9
  urshl d7, d8, d9
  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)03090b191e1f3f51inst 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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915000096041258010010080000100800005006400000200202003920039997303999780100200800002001600002003920039118020110099100100800001000000511021611200360800001002004020040200402004020040
80204200391500000041258010010080000100800005006400000200202003920039997303999780100200800002001600002003920100118020110099100100800001000000511011611200360800001002004020040200402004020040
80204200391500000041258010010080000100800005006400000200202003920039997303999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
80204200391500000041258010010080000100800005006400001200202003920039997303999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
802042003915000000516258010010080000100800005006400001200202003920039997303999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
8020420039150100480104258010010080000100800005006400001200202003920039997303999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
80204200391500003626485258010010080000100800005006400001200202003920039997303999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
80204200391500000041258010010080000100800005006400001200202003920039997303999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
80204200391500000041258010010080000100800005006400000200202003920039997303999780100200801362001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
80204200391500000041258010010080000100800005006400001200202003920039997303999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3f51inst 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)9fa8accfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039155180402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200616552003680000102004020040200402004020040
800242003915000402580010108000010800005064000020020200392003999963100198012620800002016000020039200391180021109101080000100050200516542003680000102004020040200402004020040
800242003915042303252580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200516442003680000102004020040200402004020040
80024200391504590402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200516572003680000102004020040200402004020040
800242003915000402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200616672003680000102004020040200402004020040
8002420039150420402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200516662003680000102004020040200402004020040
800242003915000402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200616652003680000102004020040200402004020040
800242003915000402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200516552003680000102004020040200402004020040
8002420039150180402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200516652003680000102004020040200402004020040
800242003915000402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200516672003680000102004020040200402004020040