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, 2S)

Test 1: uops

Code:

  uqshl v0.2s, v0.2s, #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)03080b18191e1f3f4e51inst 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)a0a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715000000611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715000000611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715000000941686251000100010002645210201820372037157131895115210001000203720371110011000000073116111786100020382038203820382038
1004203715000000611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203716000000611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715000000611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715000000611686251000100010002645211201820372037157131895100010001000203720371110011000001073116111786100020382038203820382038
1004203715000000821686251000100010002645211201820372037157431895100010001000203720371110011000000073116111786100020382038203820382038
1004203715000000611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715000000611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  uqshl v0.2s, v0.2s, #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)03080b18191e1f3a3f4e51inst 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
1020420037150000018006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715000000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715100000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000024006119686251010010010000100100005002847521020018200372003718424318760102722041016520210166201222008621102011009910010010000100000102208571011611197910100001002003820038200382003820038
1020420085150000015610406119686251010010010000100100005002847521020018200372003718421718763101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200841510000000611967525101001001000010010000653285257702016220262202751843225187451074121410660220108292022820229611020110099100100100001000030128003735156221996928100001002027820280202762022920278
1020420277152015066335202548196301261017712510060134107606562852577120162202722027618429231883810742218103942121083220276202666110201100991001001000010040201010048827157211997021100001002027620279202792027820277
1020420273151105454044012127196201041019213010012139107606852853761120198203112027818425291883610898220104992141083220275202786110201100991001001000010004210211948847264122000328100001002032720087202752032520374
1020420322151110000012019686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000371011611197910100001002003820038200382003820038
102042003715000000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150012611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150030611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500342611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216231978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150018941968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150027611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010100640216221978610000102003820038200382003820038
10024200371500366611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150090611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  uqshl v0.2s, v8.2s, #3
  uqshl v1.2s, v8.2s, #3
  uqshl v2.2s, v8.2s, #3
  uqshl v3.2s, v8.2s, #3
  uqshl v4.2s, v8.2s, #3
  uqshl v5.2s, v8.2s, #3
  uqshl v6.2s, v8.2s, #3
  uqshl v7.2s, v8.2s, #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)030708090a0b18191e1f3a3f51inst 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)9fa0a6a8a9acafc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591500000000000296280108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
80204200381500000000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
802042003815000000001200292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
80204200381500000000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
802042003815000000002100292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111518501600200350800001002003920039200392003920039
80204200381500000000300292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
80204200381500000000900292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
80204200381500000000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
80204200381500000000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000010000111511801600200350800001002003920039200392003920039
80204200381490000000900292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000007111511801600200350800001002003920039200392003920039

1000 unrolls and 10 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)9fa0a1a6a7a8a9acc2cfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500000120392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050200216322003580000102003920039200392003920039
800242003815000001980392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050200316322003580000102003920039200392003920039
80024200381500000120392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050200216232003580000102003920039200392003920039
8002420038150000000612580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050200416222003580000102003920039200392003920039
8002420038150000000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050200216222003580000102003920039200392003920039
80024200381500000240392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050200216222003580000102003920039200392003920039
800242003815000003810392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050200216232003580000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050200316222003580000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050200216222003580000102003920039200392003920039
8002420038150000000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050200316222003580000102003920039200392008820039