Apple M1 Microarchitecture Research by Dougall Johnson

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

SHLL2 (vector, 4S)

Test 1: uops

Code:

  shll2 v0.4s, v0.8h, #16
  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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371501031686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037156611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000173116111786100020382038203820382038
10042037160611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  shll2 v0.4s, v0.8h, #16
  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)03081e3f4e51inst 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)9fa8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100030071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500426119686251010012610000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100030071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100030071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686441010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100030071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03193f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715606119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000104896402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
100242003715506119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000101736402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
100242003715007261968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010136402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010036402162219786010000102003820038200382003820038
10024200371490611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010036402162219786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000101206402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  shll2 v0.4s, v8.8h, #16
  shll2 v1.4s, v8.8h, #16
  shll2 v2.4s, v8.8h, #16
  shll2 v3.4s, v8.8h, #16
  shll2 v4.4s, v8.8h, #16
  shll2 v5.4s, v8.8h, #16
  shll2 v6.4s, v8.8h, #16
  shll2 v7.4s, v8.8h, #16
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

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)9fa7a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571502925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010001011151180160020035800001002003920039200392003920039
80204200381502925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
802042003815029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100056011151180160020035800001002003920039200392003920039
802042003815064278011610080016100800285006401961200282004820048997610998680128200800382008003820048200481180201100991001008000010000022251281231120045800001002004920049200502004920050
80204200491506426801161008001610080028500640196120028200482004899769998680128200800382008003820048200481180201100991001008000010001022251291231120045800001002004920049200492004920049
802042004915064268011610080016100800285006401960200282004820048997610998680128200800382008003820049200491180201100991001008000010000022251291231120046800001002004920049200502004920050
80204200481506426801161008001610080028500640196120028200482004999761099868012820080038200800382004820048118020110099100100800001000017422251281231120045800001002004920049200502004920049
80204200481506427801161008001610080028500640196120028200482004899769998680128200800382008003820048200481180201100991001008000010001022251281231120045800001002004920049200492004920049
80204200481516427801161008001610080028500640196020028200482004999769998680128200800382008003820049200481180201100991001008000010004022251281231120045800001002004920050200502005020050
80204200491506427801161008001610080028500640196020028200492004899769998680128200800382008003820048200481180201100991001008000010000022251291231120045800001002004920049200502004920050

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030708090a18191e1f3a3f51inst 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)9fa0a1a6a8a9acc2cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501501001000024625800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100001000502400221622232003580000102003920039200392003920039
80024200381501001000028825800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100000000502400181623192003580000102003920039200392003920039
8002420038150100100002120925800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100001000502400231620202003580000102003920039200392003920039
80024200381501001000024625800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000000502400221617212003580000102003920039200392003920039
800242003815010010000252125800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000000502400221619192003580000102003920039200392003920039
80024200381501001000028825800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100000000502400221622222003580000102003920039200392003920039
80024200381501001000026725800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000000502400201621202003580000102003920039200392003920039
80024200381501001000028825800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000000502400201622222003580000102003920039200392003920039
80024200381501001000026925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100002000502400181623212003580000102003920039200392003920039
80024200381501001000024625800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000000502400211617212003580000102003920039200392003920039