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, 8H)

Test 1: uops

Code:

  urshl v0.8h, v0.8h, v1.8h
  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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100073216222630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100073216222630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100073216222630100030383038303830383038
1004303723061254825100010001000398313130183037303724153291410001000200030373037111001100073216222630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001032200030373037111001100073216222630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100073216222630100030383038303830383038
10043037220251254825100010001000398313130183037303724153289510001000200030373037111001100073116222630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100073216222630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100073216222630100030383038303830383038
1004303722061254825100010001000398313130183037303724153289510001000200030373037111001100073216222630100030383038303830383038

Test 2: Latency 1->2

Code:

  urshl v0.8h, v0.8h, v1.8h
  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)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)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)9fa1a7a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225006129548251010010410000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100004071001161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071001161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000071001161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000071001161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100001071001161129634100001003003830038300383003830038
10204300372240061295482510112127100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000046371001161129634100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000071001161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100001071001161129634100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100004071001161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100002071001161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst 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)9fa0a1a8acafc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006403162229630010000103003830038300383003830038
1002430037225000000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037224000000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037224000000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100003006402162229630010000103003830038300383003830038
1002430037225000000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  urshl v0.8h, v1.8h, v0.8h
  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)030918191e1f3f4e51inst 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002022033030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000010071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722400000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000010071011611296340100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000370071011611296340100001003003830038300383003830038
10204300372250000014729548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000470071011611296340100001003003830038300383003830038
102043003722400000612954825101001001000010010000511427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b1e1f3f4e51inst 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)9fa1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001001306640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101029850427731313001803003730037282873287671001020100002020000300373003711100211091010100001003200640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001003803640316332963010000103003830038300383003830038
10024300372240030612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001002803640316332963010000103003830038300383003830038
100243003723300120612954825100101010000111000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001003103640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001002903640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101059650427731313001803003730037282873287671001020100002020000300373003711100211091010100001004303640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001003603640316332963010000103003830038300383003830038
100243003722500088612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001003106640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001004206640316332963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  urshl v0.8h, v8.8h, v9.8h
  urshl v1.8h, v8.8h, v9.8h
  urshl v2.8h, v8.8h, v9.8h
  urshl v3.8h, v8.8h, v9.8h
  urshl v4.8h, v8.8h, v9.8h
  urshl v5.8h, v8.8h, v9.8h
  urshl v6.8h, v8.8h, v9.8h
  urshl v7.8h, v8.8h, v9.8h
  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)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)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
802042004815004125801001008000010080000500640000200200200392003999733999780100200800002001600002003920039118020110099100100800001000051103161120036800001002004020040200402004020040
802042003915504125801001008000010080000500640000200200200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915094125801001008000010080000500640000200200200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000200200200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000200200200392003999733999780100200800002001600002003920039118020110099100100800001000951101491120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000020020020039200399973399978010020080000200160000200392003911802011009910010080000100015651101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000200200200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000200200200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000200200200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000200200200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)033f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050202161120036080000102004020040200402004020040
8002420039150402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050201161120036080000102004020040200402004020040
8002420039150402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050201161120036080000102004020040200402004020040
8002420039150402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050201161120036080000102004020040200402004020040
8002420039150402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050201161120036080000102004020040200402004020040
8002420039150402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050201161120036080000102004020040200402004020040
8002420039150402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050201161120036080000102004020040200402004020040
8002420039150402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000101050201161120036080000102004020040200402004020040
8002420039150402580010128000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050201161120036080000102004020040200402004020040
8002420039150402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050201161120036080000102004020040200402004020040