Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHL (immediate, vector, 8B)

Test 1: uops

Code:

  sqshl v0.8b, v0.8b, #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)03191e3f4e51inst 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
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000373116111786100020382038203820382038
1004203716006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100011573116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102022203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshl v0.8b, v0.8b, #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)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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000124196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820085
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000709196862510100100100001001015050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715012084196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001001007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010012757101161119856100001002003820038200382003820038
102042003715000147196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000084196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006404162219786010000102003820038200382003820038
10024200371500000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000010006402162219786010000102003820038200382003820038
10024200371500000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000010006402162219786010000102003820038200382003820038
10024200371500000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001020202202026613243319822010000102008520085200862008620085
100242008415011128888168196754310036111001212101526628487850200542013220084184457187861016322101682010170201322013331100211091010100001042000200506622243219858210000102008620085200852008520085
1002420037150000150103196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000000814196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000010006402162219786010000102003820038200382003820038
10024200371500000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sqshl v0.8b, v8.8b, #3
  sqshl v1.8b, v8.8b, #3
  sqshl v2.8b, v8.8b, #3
  sqshl v3.8b, v8.8b, #3
  sqshl v4.8b, v8.8b, #3
  sqshl v5.8b, v8.8b, #3
  sqshl v6.8b, v8.8b, #3
  sqshl v7.8b, v8.8b, #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)0308191e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061150000504258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118216020035800001002003920039200392003920039
802042003815000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815000029258010810080008100800205006401320200192003820038997769989801202008003220080132200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815000029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100091115118016020035800001002003920039200392003920039
802042003815000029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
8020420038150000113258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815000029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3a3f51inst 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)9fa1a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500078125800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000005020416532003580000102003920039200392003920039
800242003815000410625800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000005020516332003580000102003920039200392003920039
80024200381500026025800101080000108000050640000020019200382003899963100188001020800002080000200392003811800211091010800001000005020427332003580000102003920039200392003920039
800242003815021613253925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000015020516322003580000102003920039200392003920039
80024200381500006225800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020216242003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020216352003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020216632003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200872003811800211091010800001000005020316652003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020216322003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020316562003580000102003920039200392003920039