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, 2S)

Test 1: uops

Code:

  sqshl 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)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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073316221786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203715032016862510001000100026452102018203720371571318951000100010002037203711100110000673216221786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100001873216221786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100002173216221786100020382038203820382038
100420371508416862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371606116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshl 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000001004196862510100100100001001000050028475210200182003720037184287187401010020010008200100082003720037111020110099100100100001000000000111718001600198000100001002003820038200382003820038
10204200371500000000814196862510100100100001001000050028475210200182003720037184287187411010020010008200100082003720037111020110099100100100001000000000111718001610198440100001002003820038200382003820038
10204200371500000000611968625101001001000010010000500284752102001820037200371842861874110100200100082001000820037200371110201100991001001000010000021000111718001600198000100001002003820038200382003820038
1020420037150000000011151968625101001001000010010000500284752102001820037200371842861874110100200100082001000820037200371110201100991001001000010000010000111717001600198000100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000000710011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000000710011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000000710011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000000710011611197910100001002003820038200382003820038
10204200371500000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000019000000710011611197910100001002003820038200382003820038
10204200371500000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000029000000710011611197910100001002003820038200382003820038

1000 unrolls and 10 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
100242003715009391968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010048640216221978610000102003820038200382003820038
10024200371500522196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500206196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500957196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715001175196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216331978610000102003820038200382003820038
100242003715031206196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010220640216221978610000102003820038200382003820038
10024200371500744196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sqshl v0.2s, v8.2s, #3
  sqshl v1.2s, v8.2s, #3
  sqshl v2.2s, v8.2s, #3
  sqshl v3.2s, v8.2s, #3
  sqshl v4.2s, v8.2s, #3
  sqshl v5.2s, v8.2s, #3
  sqshl v6.2s, v8.2s, #3
  sqshl 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)033f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150502580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160120035800001002003920039200392003920039
8020420038150922580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150522580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381502925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010001811151180160120035800001002003920039200392003920039
8020420038150292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381501172580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381501242580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b18191e1f3f5051inst 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)9fa0a1a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150000000010620022258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000050200316232003580000102003920039200392003920039
80024200381500000000390258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000050200216232003580000102003920039200392003920039
80024200381500000000810258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000050200316332003580000102003920039200392003920039
800242003815000000001060258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000050200216332003580000102003920039200392003920039
80024200381500000000390258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000050200316332003580000102003920039200392003920039
80024200381500000000390258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000050200216232003580000102003920039200392003920039
80024200381500000000390258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000050200216432003580000102003920039200392003920039
80024200381500000000390258019910800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000050200316322003580000102003920088200392003920039
800242003815000000001520258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000050200316332003580000102003920039200392003920039
80024200381500000000600258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010020000050200535332003580000102003920039200392003920039