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, 2D)

Test 1: uops

Code:

  sqshl 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)031e3f4e51inst 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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037160611686251000100010002645211201820372037157131895100010001000203720371110011000073216111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371651611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037160611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037160611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037160841686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshl 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)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)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)9fa0a1a6a8a9acc2c5cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500056106119675251010010010000100101525002847521120018020086200841842131874510100200101642001000020037200371110201100991001001000010000000000074021632197910100001002003820038200382003820038
10204200841500040506119686251010010010000100100005002847521120018020037200371842571874510100200100002001000020037200371110201100991001001000010000000000071021622197910100001002003820038200382003820038
10204200371500036306119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010000000000071021632197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847287020018020037200371842131874510100200100002001000020037200371110201100991001001000010000010000071021622197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010000000000071021622197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010000000000071022522197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010000000000071021622197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002850049120018020084200851843231874510100200100002001000020037200371110201100991001001000010000020600071021622197910100001002003820038200382003820038
102042003715001008219686251010010010000100100005002847521120018020037200371842131874510100204100002001000020037200371110201100991001001000010000000203000073522423198230100001002027520228202302027520180
102042027515154267440250519642104101911311006013910608679284866502016202027820268184352118835108992081079622010828202752022761102011009910010010000100220109708000824257421993224100001002022720279202692027820279

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371560000000061196862510010101000010100005028475211200182003720083184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000000000536196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000000061196752510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sqshl v0.2d, v8.2d, #3
  sqshl v1.2d, v8.2d, #3
  sqshl v2.2d, v8.2d, #3
  sqshl v3.2d, v8.2d, #3
  sqshl v4.2d, v8.2d, #3
  sqshl v5.2d, v8.2d, #3
  sqshl v6.2d, v8.2d, #3
  sqshl 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): 0.2506

retire (01)cycle (02)0307080a0b18191e1f3f51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815000000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511841634200350800001002003920039200392003920039
8020420038150000000002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000045000111511831634200350800001002003920039200392003920039
802042003814900000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511831624200350800001002003920039200392003920039
802042003815000000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511831634200350800001002003920039200392003920039
8020420038150000000150292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511831633200350800001002003920039200392003920039
8020420038150000000360292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511841634200350800001002003920039200392003920039
802042003815000000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511831643200350800001002003920039200392003920039
802042003815000000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511831633200350800001002003920039200392003920039
802042003815000000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511841624200350800001002003920039200392003920039
80204200381500000002220292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511841634200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b18191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115000000300039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020316232003580000102003920039200392003920039
800242003815000000150039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020316322003580000102003920039200392003920039
80024200381500000060039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020216332003580000102003920039200392003920039
800242003815000000180039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020216322003580000102003920039200392003920039
8002420038150000002550039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020316322003580000102003920039200392003920039
80024200381500000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020316322003580000102003920039200392003920039
80024200381500000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020316322003580000102003920039200392003920039
80024200381500000000039258008610800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020216332003580000102003920039200392003920039
80024200381500000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020316322003580000102003920039200392003920039
80024200381500000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020316232003580000102003920039200392003920039