Apple M1 Microarchitecture Research by Dougall Johnson

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

SHLL (vector, 8H)

Test 1: uops

Code:

  shll v0.8h, v0.8b, #8
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116211786100020382038203820382038
100420371596116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100003073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  shll v0.8h, v0.8b, #8
  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)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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500347196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001001007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200182003720037184213187451010020010176200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150084196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150082196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001001007101161119791100001002003820038200382003820038
10204200371500149196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

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)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)9fa0a1a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000124196862510010101000010100005028475210200182003720085184473187671001020100002010000200372003711100211091010100001020003944206402162219786010000102008620086200382003820084
1002420037150111061196662510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000170196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000003006402162219786010000102003820038200382003820038
100242003715000012212196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242008515000021293196862510010101000010100005028475211200182003720037184433187671001020100002010000200852003711100211091010100001000020006402162219786010000102003820038200382003820038
1002420037150000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037149000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000406402162219786010000102003820038200382003820038
10024200371500000687196862510024101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  shll v0.8h, v8.8b, #8
  shll v1.8h, v8.8b, #8
  shll v2.8h, v8.8b, #8
  shll v3.8h, v8.8b, #8
  shll v4.8h, v8.8b, #8
  shll v5.8h, v8.8b, #8
  shll v6.8h, v8.8b, #8
  shll v7.8h, v8.8b, #8
  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)031e3f51inst 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)9fa1acc5branch mispredict (cb)cdcfd6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150950258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160020035800001002003920039200392003920039
80204200381500261258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100401115118160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160020035800001002003920039200392003920039
802042003815001091258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118161020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160020035800001002003920039200392003920039
8020420038150329258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst 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)9faccfd0d2d5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500188258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001005020002165222003580000102003920039200392003920039
80024200381500125258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001005020002163222003580000102003920039200392003920039
80024200381500102258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001005020002163222003580000102003920039200392003920039
80024200381500134258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001005020002163222003580000102003920039200392003920039
80024200381500144258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001005020002163222003580000102003920039200392003920039
8002420038150039258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001005020002163332003580000102003920039200392003920039
80024200381500209258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001005020002163232003580000102003920039200392003920039
8002420038150062258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001005020002163222003580000102003920039200392003920039
80024200381500392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010275020002163222003580000102003920039200392003920039
8002420038150060258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001005020002163322003580000102003920039200392003920039