Apple M1 Microarchitecture Research by Dougall Johnson

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

UADDLP (vector, 1D)

Test 1: uops

Code:

  uaddlp v0.1d, v0.2s
  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
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000373116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371566116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371606116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371606116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  uaddlp v0.1d, v0.2s
  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)0318191e1f3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000066196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000726196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200902003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200852003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500039061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150006061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200862003820038

1000 unrolls and 10 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371550661968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371560611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
100242003715093611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  uaddlp v0.1d, v8.2s
  uaddlp v1.1d, v8.2s
  uaddlp v2.1d, v8.2s
  uaddlp v3.1d, v8.2s
  uaddlp v4.1d, v8.2s
  uaddlp v5.1d, v8.2s
  uaddlp v6.1d, v8.2s
  uaddlp v7.1d, v8.2s
  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)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)9fa8acc5branch mispredict (cb)cdcfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150292580108100800081008002050064013205200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118516165420035800001002003920039200392003920039
80204200381502925801081008000810080020500640132152001920038200389977699898012020080032200800322003820038118020110099100100800001002401115118515163320035800001002003920039200392003920039
802042003815515742580108100800081008002050064013215200192003820038997769989801202008003220080032200382003811802011009910010080000100601115118514164420035800001002003920039200392003920039
8020420038150292580108100800081008002050064013215200192003820038997769989801202008003220080032200382003811802011009910010080000100031115118515164520035800001002003920039200392003920039
8020420038150292580108100800081008002050064013215200192003820038997769989801202008003220080032200382003811802011009910010080000100131115118004165420035800001002003920039200392003920039
8020420038150292580108100800081008002050064013210200192003820038997769989801202008003220080032200382003811802011009910010080000100201115118514165520035800001002003920039200392003920039
8020420038150292580108100800081008002050064013210200192003820038997769989801202008003220080032200382003811802011009910010080000100301115118515165420035800001002003920039200392003920039
8020420038150292580108100800081008002050064013205200192003820038997769989801202008003220080032200382003811802011009910010080000100131115118005165420035800001002003920039200392003920039
8020420038150292580108100800081008002050064013215200192003820038997769989801202008003220080032200382003811802011009910010080000100101115118005164420035800001002003920039200392003920039
8020420038150292580108100800081008002050064013210200192003820038997769989801202008003220080032200382003811802011009910010080000100031115118515165520035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b18191e1f3f51inst 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)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115000000003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000051012050201161120035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100003409050201161120035080000102003920039200392003920039
80024200381500000000392580010108000010802945064000012001920038200389996310018800102080000208000020038200381180021109101080000100000087450201161120035080000102003920039200392003920039
8002420038150000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000109050201161120035080000102003920039200392003920039
8002420038150000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000050201161120035080000102003920039200392003920039
8002420038150000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000109050201161120035080000102003920039200392003920039
800242003815000000003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000141050201161120035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100000021050201391120035080000102003920039200392003920039
800242003814900000003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000102050201161120035080000102003920039200392003920039
8002420038150000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000050201161120035080000102003920039200392003920039