Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSHL (immediate, vector, 4S)

Test 1: uops

Code:

  uqshl v0.4s, v0.4s, #3
  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)696d6edispatch 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
1004203715001701686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506611686251000100010002645212018203720371571318951000100010002037203711100110000073116111860100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715015611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073124111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371503611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  uqshl v0.4s, v0.4s, #3
  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)030b18191e1f3f4e51inst 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)9facc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042027915215689752861196862510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000024061196862510100100100001001000050028475210200182003720037184217318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000489061196862510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500000061196862510137100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000000215196862510100100100001001000050028475211200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500000061196862510100100100001001000050028475211200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500000061196862510100100100001001000050028475211200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500000061196862510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100027101161119791100001002003820038200382003820038
102042003715000021061196862510100100100001001000050028475211200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000021061196862510100100100001001000050028475211200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 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
1002420037150001861196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001010640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500058261196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150003061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150006553196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  uqshl v0.4s, v8.4s, #3
  uqshl v1.4s, v8.4s, #3
  uqshl v2.4s, v8.4s, #3
  uqshl v3.4s, v8.4s, #3
  uqshl v4.4s, v8.4s, #3
  uqshl v5.4s, v8.4s, #3
  uqshl v6.4s, v8.4s, #3
  uqshl v7.4s, v8.4s, #3
  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)030b18191e1f3f51inst 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)9fa0a1a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059151000120292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003814900000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000411151181161120035800001002003920039200392003920039
8020420038150000150292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
8020420038155000001282580180100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080a0b18191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc2cfd2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150000000300039258001010800001080097506400001200192003820038100043100188001020800002080000200902009111800211091010800001000000000502001616171220035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000012001920099200389996310018801092080000208000020038200381180021109101080000100000006050200716171720035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050200171617620035080000102003920039200392003920039
8002420038150000000000354258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020081617820035080000102003920039200392003920039
80024200381500000000009201228038510804671280487506430941201702028220238100402510124804042080486208048720289202386180021109101080000102200022340051050157281420190080000102029520289202452028620295
800242029215201014539944019631178047510804681080484506438361202132028620288100411610151804972080483208048420290200387180021109101080000102420122088050200181661720035080000102003920039200902003920039
800242003815000000018001077118804801080557108048761643816120215202442028410040261015280496208048822800002024120286618002110910108000010000104468251060187381720229080000102034520394203402039520394
8002420340153210176951528011831578038010806551080582506438681202872034220349100473410208805972080682208058420411203887180021109101080000101000022805051240102891320419180000102044520444204942039420447
80024202421582021875557040403258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010007002281025140059792120035080000102003920039200392003920039
8002420038156000079118835202024161805741080559108068350644612120019200382003810012310018800102080099208000020038200871180021109101080000100000023753050200835171420082080000102034420538203002044420293