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, 4H)

Test 1: uops

Code:

  uaddlp v0.4h, 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)03041e3a3f4e51inst 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
10042037150026216862510001000100026452102018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
10042037150026216862510001000100026452102018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
10042037160026216862510001000100026452102018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
10042037150026216862510001000100026452102018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
10042037150026216862510001000100026452102018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
10042037150026216862510001000100026452102018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
10042037160026216862510001000100026452102018203720371571318951000100010002037203711100110000377416441786100020382038203820382038
10042037150026216862510001000100026452102018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
10042037150026216862510001000100026452102018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
10042037160026216862510001000100026452102018203720371571318951000100010002037203711100110000077416441786100020382038203820382038

Test 2: Latency 1->2

Code:

  uaddlp v0.4h, 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)03070b191e1f3f4e51inst 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)9fa1a7a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000061196862510100100100001001000062628475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000020071011611197910100001002003820038200382003820038
102042003715000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000018071011611197910100001002003820038200382003820038
10204200371500000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500000061196752510100100100001001000050028475211200182003720037184213187441010020010000200100002003720037111020110099100100100001000006071011611197910100001002003820038200382003820038
10204200371500000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000006071011611197910100001002003820038200382003820038
10204200371500000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000009071011611197910100001002003820038200382003820038
102042003715000000611968625101001251000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000018071011611197910100001002003820038200382003820038
102042003715000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000100710116111979125100001002003820038200382003820038
10204200371500000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)9fa0a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371500000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
1002420037150002160611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000306402162219786010000102003820038200382003820038
10024200371500000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010004006402162219786010000102003820038200382003820038
10024200841500000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371500000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371500000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371500000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371500000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371500000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000306402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  uaddlp v0.4h, v8.8b
  uaddlp v1.4h, v8.8b
  uaddlp v2.4h, v8.8b
  uaddlp v3.4h, v8.8b
  uaddlp v4.4h, v8.8b
  uaddlp v5.4h, v8.8b
  uaddlp v6.4h, v8.8b
  uaddlp v7.4h, 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)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)9fa8acc5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815002925801081008008010080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815032925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010010111511801620035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008012820038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010030111511801620035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815005025801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304090b1e1f3f51inst 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)9fa8a9acc2cfd2itlb miss (d4)d5d6daddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150110009342580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000502101101601815200350080000102003920039200392003920039
8002420038155110002102580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000502101141601711200350080000102003920039200392003920039
800242003815011000852580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000502101161601417200350080000102003920039200392003920039
800242003815011000852580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000502000171609162003521080000102003920039200392003920039
8002420038150110001312580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000102500050210113160179200350080000102003920039200392003920039
800242003815011000448258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000050210117160179200350080000102003920039200392003920039
80024200381501110085425800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001014000502101171601717200350080000102003920039200392003920039
800242003815011000852580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000502101171601716200350080000102003920039200392003920039
80024200381501100085258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000050210181601714200350080000102003920039200392003920039
800242003815011000852580010108000010800005064000002001920038200389996310044800102080000208000020038200381180021109101080000100000502101171601717200350080000102003920039200392008920039