Apple M1 Microarchitecture Research by Dougall Johnson

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

SSHLL (4S)

Test 1: uops

Code:

  sshll v0.4s, v0.4h, #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)a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715135611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037160611686251000100010002645210201820372037157131895100010001000203720371110011000020073116111786100020382038203820382038
10042037160611686251000100010002645210201820372037157131895100010001000203720371110011000040073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038207520862038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
100420371554611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
100420371548611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
100420371533611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  sshll v0.4s, v0.4h, #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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150636119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150156119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715006119686251010010010048100100005002847521200182003720037184213187451010020010000200101672003720037111020110099100100100001000371011611197910100001002003820038200382003820038
1020420037150156119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150246119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150126119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037149276119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150246119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150276119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080a0b18191e1f3f4e51inst 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
100242003715000000153061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010101525028487851200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000306402162219786010000102003820038200382003820038
10024200371500000015061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000109061196862510010101000013100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000012061196862510010101001210100005028475211200182003720132184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000018061196862510010121000010100006028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000306402162219786010000102003820038200382003820038
100242003715000001330103196862510010101000010100005028475210200182003720037184433187671016220100002010000200372003711100211091010100001000000606682162219822010000102003820038200382003820038
10024200371500000024061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000020006402162219786010000102003820038200382003820085
10024200371500000090103196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000306402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sshll v0.4s, v8.4h, #3
  sshll v1.4s, v8.4h, #3
  sshll v2.4s, v8.4h, #3
  sshll v3.4s, v8.4h, #3
  sshll v4.4s, v8.4h, #3
  sshll v5.4s, v8.4h, #3
  sshll v6.4s, v8.4h, #3
  sshll v7.4s, v8.4h, #3
  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)03080b18191e1f3f51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
80204200381500000002682580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
80204200381500000006942580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000006030111511801600200350800001002003920039200392003920039
8020420038150000030292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
80204200381500000150292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03071e3f51inst 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)9fa8c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020516432003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020216442003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020216422003580000102003920039200392003920039
800242003815003939258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020416442003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020216442003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200232003820038999631001880010208000020800002003820038118002110910108000010105020416422003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020416442003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020416442003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020416422003580000102003920039200392003920039
80024200381501039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020416422003580000102003920039200392003920039