Apple M1 Microarchitecture Research by Dougall Johnson

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

UADDLP (vector, 2D)

Test 1: uops

Code:

  uaddlp v0.2d, v0.4s
  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)03091e3f4e51inst 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)a0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203716006116862510001000100026452120182037203715713189510001000100020372037111001100000373116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000673116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100001073116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004208516006116862510001000100026452120182037203715713189510001000100020372037111001100040073116111786100020382038203820382038
1004203716006116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111002100000073116111786100020382038203820382038
1004203716006116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038208520742038

Test 2: Latency 1->2

Code:

  uaddlp v0.2d, v0.4s
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

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)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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010003071021622197910100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200182003720084184213187451010020010000200100002003720037111020110099100100100001000484271021622197910100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010002071021622197910100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010001071021622197910100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000671021622197910100001002003820038200382003820038
102042003715001031968625101001001000010010000500284752102001820037200371842731874510256200100002001000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
1020420037150061196861031010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100036071021622197910100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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)9fa8acc5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010321200640216221978610000102003820038200382003820038
10024200841500611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000105600640216221978610000102003820038200382003820038
10024200371500821968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686451001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001034000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000103310640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752120018200372003718443318767100102010000201000020084200371110021109101010000102000640216221978610000102003820038200382003820038
10024200371500611968625100101010036101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000104511700640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  uaddlp v0.2d, v8.4s
  uaddlp v1.2d, v8.4s
  uaddlp v2.2d, v8.4s
  uaddlp v3.2d, v8.4s
  uaddlp v4.2d, v8.4s
  uaddlp v5.2d, v8.4s
  uaddlp v6.2d, v8.4s
  uaddlp v7.2d, v8.4s
  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)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)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)9fa1a8acc5branch mispredict (cb)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420068150292580108100800081008031650064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000061115118116020085800001002003920039200392003920039
8020420038150292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001002501115118016020035800001002003920039200392003920039
8020420038150292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000101115118016020035800001002003920039200392003920039
8020420038150292580108100800081008002050064013202006820038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e3f51inst 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)9fa7a8a9c2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500012325800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000005020221619182003580000102003920039200392003920039
8002420038150003925800101080000108009950640000020019200382003899963100188001020800002080000200382003811800211091010800001000005020181612232003580000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000005020171617112003580000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000005020161617162003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020201618122003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020171615122003580000102003920039200392003920039
80024200381500027325800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000005020171619192003580000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000005020171618132003580000102003920039200392003920039
8002420038150034732580010108000010800005064000002001920038200389996310018800102080000208000020090200381180021109101080000100000502018161792003580000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000005020171616172003580000102003920039200392003920039