Apple M1 Microarchitecture Research by Dougall Johnson

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

REV32 (vector, 8B)

Test 1: uops

Code:

  rev32 v0.8b, v0.8b
  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)03081e3f4e51inst 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
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073216111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110006073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715096116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110002373116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715008416862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  rev32 v0.8b, v0.8b
  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)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)72scheduler 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500302196862510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200182003720037184217318745101002001000020010000200372003711102011009910010010000100007101161219791100001002003820038200382003820038
10204200371500189196534410100118100121001000050028475211200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150161196862510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161219791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101162119791100001002017920038200382003820038
10204200371500103196752510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101162119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030818191e1f3f4e51inst 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
100242003715000000218196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006403163319786010000102003820038200382003820038
10024200371500000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006403163319786010000102003820038200382003820038
10024200371500000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006403163319786010000102003820038200382003820038
10024200371500000073196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006403163319786010000102003820038200382018120038
10024201301500000084196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006403163319786010000102003820038200382003820038
10024200371490000084196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006403163319786010000102003820038200382003820038
100242003715000000126196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006403163319786010000102003820038200382003820038
100242003715000000156196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006403163319786010000102003820038200382003820038
10024200371500000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006403163319786010000102003820038200382003820038
100242003715000000126196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006403163319786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  rev32 v0.8b, v8.8b
  rev32 v1.8b, v8.8b
  rev32 v2.8b, v8.8b
  rev32 v3.8b, v8.8b
  rev32 v4.8b, v8.8b
  rev32 v5.8b, v8.8b
  rev32 v6.8b, v8.8b
  rev32 v7.8b, v8.8b
  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)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)9fa0a1a6a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715000000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511811600200350800001002003920039200392003920039
802042003815000000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
80204200381500000001133258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
802042003815000000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
802042003815000000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
802042003815000000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
802042003815000000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
802042003815000000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
802042003815000000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
8020420038150000000504258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039

1000 unrolls and 10 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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020516652003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020916662003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020716652003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020816672003580000102003920039200392003920039
8002420038150006043800101080000108000050640000120019200382003899963100188010920800002080000200382003811800211091010800001001005022516462003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010443050205161042003580000102003920039200392003920039
8002420038150008125800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020716562003580000102014120039201422003920039
80024200381503883925800101080000108000050640000120019200382003899968100468001020800002080000200382003811800211091010800001000305020616442003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020616662003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001001005020516642003580000102003920039200392008920039