Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHL (immediate, vector, 4S)

Test 1: uops

Code:

  sqshl 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)03191e3f4e51inst 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
1004203715008216862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020852038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716106116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715096116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshl 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)0308191e1f3f4e51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752112001820037200861843231874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000001031968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007102161119791100001002003820038200382003820038
1020420037150001201031968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000137101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820084200371842131874510100200100002001000020037200371110201100991001001000010000137101161119791100001002003820038200382003820038
10204200371490000611968625101381151000010010000500284878502001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371490000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090a0b18191e1f3a3f4e51inst 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)9fa0a1a6a7a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003714900000000082196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000000000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000000000061196862510048121001210100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200852003820038
100242003715000000000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820086
100242003715000000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820302
1002420273152111077924616034951959815810024161008412110647128578370200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000000000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000000088061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000000000103196862510010101000010100007128475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000000000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219931010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sqshl v0.4s, v8.4s, #3
  sqshl v1.4s, v8.4s, #3
  sqshl v2.4s, v8.4s, #3
  sqshl v3.4s, v8.4s, #3
  sqshl v4.4s, v8.4s, #3
  sqshl v5.4s, v8.4s, #3
  sqshl v6.4s, v8.4s, #3
  sqshl 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)03080b18191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915000000002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
802042003815000000002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
8020420038150000000050425801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511831600200350800001002003920039200392003920039
802042003815000000002925802041008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
802042003815000000002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
802042003815000000002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
802042003815000000005225801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
802042003815000000002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
802042003815600000002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
802042003815000000002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039

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)6061696d6edispatch 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)9fa0a1a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115000000003925800101080000108000050640000102001920038200389996031001880010208000020800002003820038118002110910108000010000000050200716322003580000102003920039200392003920039
800242003815000000003925800101080000108000050640000102001920038200389996031001880010208000020800002003820038118002110910108000010000000050200329662003580000102003920039200392003920039
800242003815000000003925800101080000108000050640768102001920038200389996031001880010208000020800002003820038118002110910108000010000000050200216552003580000102003920039200392003920039
800242003815000000003925800101080000108000050640000102001920038200389996031001880010208000020800002003820038118002110910108000010000000050200316262003580000102003920039200392003920039
800242003815000000003925800101080000108000050640000102001920038200389996031001880010208000020800002003820038118002110910108000010000000050200516632003580000102003920039200392003920039
800242003815000000003925800101080000108000050640000002001920038200389996031001880010208000020800002003820038118002110910108000010000000050200316552003580000102003920039200392003920039
8002420038150000000070425800101080000108000050640000002001920038200389996031001880010208000020800002003820038118002110910108000010000000050200316632003580000102003920039200392003920039
8002420038150000000092012480388108046711800005064384000202102028920285100270161007280499248048720803882029220293318002110910108000010043142583050200363752022980000102024420289202862029120295
80024202861520115566044097612180477108000010803895064385000201722029020291100380321015380398208048320801932019020285618002110910108000010440102315050710516232003580000102003920039200392003920039
80024200381500000026417639103800101080376108039050643812002013820240202821004002610124803952080487208048820285201842180021109101080000102200023452505401273232022880000102029120294202882028920242