Apple M1 Microarchitecture Research by Dougall Johnson

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

SADDLP (vector, 8H)

Test 1: uops

Code:

  saddlp v0.8h, v0.16b
  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)03081e3f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037160061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000373116111786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037160061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  saddlp v0.8h, v0.16b
  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)030b18191e1f3f4e51inst 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)6061696d6edispatch 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)9fa8accfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000012061196862510100100100001001000050028475211520018200372003718421318745101002001000020010000200372003711102011009910010010000100037105111611197910100001002003820038200382003820038
1020420037150000180536196862510100100100001001000050028475210520018200372003718421318745101002001000020010000200372003711102011009910010010000100007100111612197910100001002003820038200382003820038
10204200851500032701078196862510100100100001001000055328475210520018200372003718421318745101002001000020010000200372003711102011009910010010000100107105011611197910100001002003820038200382013320038
102042003715000030523196862510100100100001001000050028475210520018200372003718421318745101002001000020010000200372003711102011009910010010000100007100011611197910100001002003820038200382003820038
1020420037150000635261196862510100100100001001000050028475211020018200372003718421318745101002001000020010000200372003711102011009910010010000100007100011621197910100001002003820038200382003820038
102042003715000018061196866310100122100001001000050028475210520018200372003718421318745101002001000020010000200372003711102011009910010010000100007100011611197910100001002003820038200382003820038
102042003715000018061196752510100100100001001000050028475210520018200372003718421318745101002001000020010000200372003711102011009910010010000100007105112511197910100001002003820038200382003820038
102042003715000036061196862510100100100001001000050028475211020018200372003718421318745101002001000020010000200372003711102011009910010010000100007105111611197910100001002003820038200382003820038
102042003715000027061196862510100100100001001000050028475211020018200372003718421318745101002001000020010000200372003711102011009910010010000100007105111621198220100001002003820038200382003820038
102042003715000027061196862510100100100001001000050028513130520018200372003718421318745101002001000020010000200372003711102011009910010010000100007105111611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030918191e3f4e51inst 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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000030611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640316221978610000102003820038200382003820038
10024200371500000611967525100101010000101000050284752120018200372003718443318767100102010337201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371500000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100100640216221978610000102003820038200382003820038
10024200371500000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715000048611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715000033611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715000045611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371500000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200831110021109101010000100000640216221978610000102003820038200382003820038
10024200371500009611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371500001629431968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  saddlp v0.8h, v8.16b
  saddlp v1.8h, v8.16b
  saddlp v2.8h, v8.16b
  saddlp v3.8h, v8.16b
  saddlp v4.8h, v8.16b
  saddlp v5.8h, v8.16b
  saddlp v6.8h, v8.16b
  saddlp v7.8h, v8.16b
  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)031e3a3f51inst 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)9fa1a6a9acc2c5branch mispredict (cb)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150450292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
80204200381502430292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
8020420038150180292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
802042003814900292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)9fa6a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000205020316552003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020616652003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020516652003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020216542003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000105020316552003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000205020616232003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000105020316322003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100478001020800002080000200382003811800211091010800001000505020216552003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010006605038516332011280000102003920039200392003920089
800242003815001394380010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100001835020316652003580000102003920039200392003920039