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, 2D)

Test 1: uops

Code:

  uqshl v0.2d, v0.2d, #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)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
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073216111786100020382038203820382038
1004203716006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  uqshl v0.2d, v0.2d, #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)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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007581161119791100001002003820038200382003820038
102042003715006119686251010010010000104100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

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)9fa0a1a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038
100242003715000661196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000724216221978610000102003820038200382003820038
1002420037150000536196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640216211978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  uqshl v0.2d, v8.2d, #3
  uqshl v1.2d, v8.2d, #3
  uqshl v2.2d, v8.2d, #3
  uqshl v3.2d, v8.2d, #3
  uqshl v4.2d, v8.2d, #3
  uqshl v5.2d, v8.2d, #3
  uqshl v6.2d, v8.2d, #3
  uqshl v7.2d, v8.2d, #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)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)60696b6d6edispatch 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)9fa0a1a6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061150000000000292580108100800081008002050064013212006702003820038997769989801202008003220080032200382003811802011009910010080000100000000111511811600200350800001002003920039200392003920039
8020420038150000000000292580108100800081008002050064013202001902003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
80204200381500000000006942580108100800081008002050064013202001902003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
8020420038150000000000292580108100800081008002050064013202001902003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
8020420038150000000000292580108100800081008002050064013212001902003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
80204200381500000000002925801081008000810080020500640132020019020038200389977699898012020080032200800322003820038118020110099100100800001000000900111511801600200350800001002003920039200392003920039
8020420038150000000000292580108100800081008002050064013212001902003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
8020420038149000000000292580108100800081008002050064013212001902003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
8020420038150000000000292580108100800081008002050064013202001902003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
80204200381500000000002925801081008000810080020500640132120019020038200389977699898012020080032200800322003820038118020110099100100800001000001120111511801600200350800001002003920039200392003920039

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)5f60696b6d6edispatch 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)9fa1a6a7a8a9acc2cfd0d5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000000081258001010800001080000506400000120019020038200389996310018800102080000208000020038200381180021109101080000100000000502006160242003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000120019020038200389996310018800102080000208000020038200381180021109101080000100000000502004160242003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000120019020038200389996310018800102080000208000020038200381180021109101080000100000000502002160422003580000102003920039200392003920039
800242003815000000039258001010800001080097506400000120057020038200389996310018800102080000208000020038200381180021109101080000100000002502004160442003580000102003920039200392003920039
800242003815000000039258001010800941080000506400000120019020038200389996310018800102080000208000020038200381180021109101080000100000000502004160422003580000102003920039200392003920039
800242003815000000081258001010800001080000506400000120019020038200389996310018800102080000208000020038200381180021109101080000100000000502004160242003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000120019020038200389996310018800102080000208000020038200381180021109101080000100000000502004160242003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000120019020038200389996310018800102080000208000020038200381180021109101080000100000000502004160422003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000120019020038200389996310018800102080000208000020038200381180021109101080000100000000502006160422003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000120019020038200389996310018800102080000208000020038200381180021109101080000100000000502002160422003580000102003920039200392003920039