Apple M1 Microarchitecture Research by Dougall Johnson

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

RBIT (vector, 8B)

Test 1: uops

Code:

  rbit 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)030708090a1e3a3f4e51inst 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
10042037151001026816862510001000100026452112018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
10042037151001026816862510001000100026452112018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
10042037151001026816862510001000100026452112018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
10042037151001026816862510001000100026452112018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
10042037151001026816862510001000100026452112018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
10042037151001026816862510001000100026452112018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
10042037151001026816862510001000100026452112018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
10042037151001026816862510001000100026452112018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
10042037151001026816862510001000100026452112018203720371571318951000100010002037203711100110002077416441786100020382038203820382038
1004203715100102681686251000100010002645211201820372037157131895100010001000203720371110011000015977416441786100020382038203820382038

Test 2: Latency 1->2

Code:

  rbit 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)0318191e3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150011656119686251010010010000100100005002847521120018200372003718421318762101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475210200182003720037184212518745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715010126119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000360061196862510010101000010100005028475211200182003720085184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000000240061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000000000536196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000001006402162219786010000102003820038200382003820038
1002420037150000002100611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000366402162219786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000060061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000000061196752510010101000010100005028475211200182003720037184433187671001020100002010000200372003721100211091010100001000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  rbit v0.8b, v8.8b
  rbit v1.8b, v8.8b
  rbit v2.8b, v8.8b
  rbit v3.8b, v8.8b
  rbit v4.8b, v8.8b
  rbit v5.8b, v8.8b
  rbit v6.8b, v8.8b
  rbit 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)0318191e3f51inst 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)9fa6a8a9acc2c5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150006029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
802042003815000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100010001115136016020035800001002003920039200392003920039
8020420038150009115258010810080008100800205006401321200192003820038997769989801202008003220080032202392003811802011009910010080000100000001115118016020035800001002003920039200392003920039
8020420038150001529258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
8020420038150002732925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000058601115118016020035800001002003920039200392003920039
802042003815000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
802042003815000447294258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
802042003815000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100200001115118016020035800001002003920039200392003920039
802042003815000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
80204200381501020129258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e3f51inst 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)9fa0a8accfd5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150002189425800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001020050206160552003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050203160352003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000350205160532003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050205160532003580000102003920039200392003920039
800242003815000022925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050205160532003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050205160352003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050203160532003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050205160532003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050205160532003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050205160352003580000102003920039200392003920039