Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHLU (scalar, S)

Test 1: uops

Code:

  sqshlu s0, s0, #3
  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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000265785020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshlu s0, s0, #3
  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)0308090a0b18191e1f3a3f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204203111521101666935281255819631122101971001006014010760644285384112020220323203211843833188591068722010831222108262032420276211020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000000000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000000210061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000000000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000000000082196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000000000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000000000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000000000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000000210061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000000000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9faccfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000462196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001006404166519786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001006406165619786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001006405166619786010000102003820038200842003820038
10024200371501061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001006406165619786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001006406166519786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001006405165519786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001006405165519786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001006406165819786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001036405165519786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001006405165419786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sqshlu s0, s8, #3
  sqshlu s1, s8, #3
  sqshlu s2, s8, #3
  sqshlu s3, s8, #3
  sqshlu s4, s8, #3
  sqshlu s5, s8, #3
  sqshlu s6, s8, #3
  sqshlu s7, s8, #3
  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)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)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)9fa8a9acc5branch mispredict (cb)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118116020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001001031115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020076800001002003920039200392003920039
80204200381500029258010810080008100801205006401321200192003820086100021299898012020080032202800322003820038218020110099100100800001000001115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001001031115118016020035800001002003920039200392003920039
8020420038150120292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212017420038200389977699898012020080032200800322003820038118020110099100100800001001431115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030a1e3f51inst 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)5f6061696d6edispatch 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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115000704258001010800001080000506400003102001920038200389996310018800102080000208000020038200381180021109101080000100050200316442003580000102003920039200392003920039
80024200381500039258001010800001080000506400002102001920038200389996310018800102080000208000020038200381180021109101080000100050200416442003580000102003920039200392003920039
80024200381500039258001010800001080000506400002102001920038200389996310018800102080000208000020038200381180021109101080000100050200316432003580000102003920039200392003920039
800242003815003939258001010800001080000506400003102001920038200389996310018800102080000208000020038200381180021109101080000100050200416352003580000102003920039200392003920039
800242003815000392580010108000010800005064000021420019200382003899963100188001020800002080000200382003811800211091010800001053050204416552003580000102003920039200392003920039
80024200381500039258001010800001080000506400003142001920038200389996310018800102080000208000020038200381180021109101080000100050200416442003580000102003920039200392003920039
80024200381500039258001010800001080000506400003102001920038200389996310018800102080000208000020038200381180021109101080000100050200316322003580000102003920039200392003920039
80024200381500039258001010800001080000506400002102001920038200389996310018800102080000208000020038200381180021109101080000100050200316442003580000102003920039200392003920039
80024200381500039258001010800001080000506400004102001920038200389996310018800102080000208000020038200381180021109101080000100050200416432003580000102003920039200392003920039
80024200381500939258001010800001080000506400004102001920038200389996310018800102080000208000020038200381180021109101080000100050200416342003580000102003920039200392003920039