Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHLU (scalar, D)

Test 1: uops

Code:

  sqshlu d0, d0, #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
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000373116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716126116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371606116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshlu d0, d0, #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)0307080b18191e1f3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000000066196862510100100100001001000050028475211200182003720037184213187441012520010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000108196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000100071011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001251000062628475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000003071011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196862510100125100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000306008071011621197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000062628475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000100071011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150100000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011622197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038

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)9fa8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000101600640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001030900640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000101257300640216221978610000102003820038200382003820038
100242003715006119686451001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000101300640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000101300640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000101300640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100300640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001021800800640216221978610000102003820038200382003820038
100242003715006119686251001012100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sqshlu d0, d8, #3
  sqshlu d1, d8, #3
  sqshlu d2, d8, #3
  sqshlu d3, d8, #3
  sqshlu d4, d8, #3
  sqshlu d5, d8, #3
  sqshlu d6, d8, #3
  sqshlu d7, d8, #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)03070a1e3f51inst 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)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)9fa6a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571501102002580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100020011151181161120035800001002003920039200392003920039
80204200381501112292580108100800081008002050064013212001920038200389977069989802242008003220080032200382003811802011009910010080000100010311151181161120035800001002003920039200392003920039
80204200381501102925801081008000810080020500640132120019200382003899770699898012020080032200800322003820038118020110099100100800001000250011151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000311151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
80204200381501102812580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013212001920038200389977061002380120200800322008003220038200381180201100991001008000010001014111151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030e1e3f51inst 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)696d6edispatch 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115020392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001052050207166162003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050206161662003580000102003920039200392003920039
800242003814900392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050206166162003580000102003920039200392003920039
80024200381500039258001010800801080000506400002001920038200389996310018800102080000208000020038200381180021109101080000103900502016161662003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001063005020161616162003580000102003920039200392003920039
8002420038150003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010200502016161642003580000102003920039200392003920039
8002420038150003925800101080000108000050640000200192003820038999631001880010208000020800002008820038118002110910108000010100502016161662003580000102003920039200392003920039
8002420038150003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000502016166162003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050206166162003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000350206161662003580000102003920039200392003920039