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, B)

Test 1: uops

Code:

  sqshlu b0, b0, #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)696d6edispatch 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
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571718951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160821686251000100010002645212018203720371571318951000100010002037203711100110000373116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037153611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshlu b0, b0, #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)030708090b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000000065519686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071031721197910100001002003820038200382003820038
10204200371500000000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011633197910100001002003820038200382003820038
1020420037150000000000134119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071021611197910100001002003820038200382003820038
10204200371500000000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000000000061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000000000710116111979125100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03181e3f4e51inst 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)9fa0a8acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000124196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006404164419786010000102003820038200382003820038
100242003715000251196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006404164419786010000102003820038200382003820038
10024200371490061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006404163419786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006404165419786010000102003820038200382003820038
10024200371501084196862510010101000010100005028475212001820037200371844331878510010201000020100002003720037111002110910101000010000006403164419786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006404164419786010000102003820038200382003820038
10024200371500094196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006403165419786010000102003820038200382003820038
100242003715000145196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006404165419786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006404164419786010000102003820038200382003820038
100242003715000195196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006404164419786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sqshlu b0, b8, #3
  sqshlu b1, b8, #3
  sqshlu b2, b8, #3
  sqshlu b3, b8, #3
  sqshlu b4, b8, #3
  sqshlu b5, b8, #3
  sqshlu b6, b8, #3
  sqshlu b7, b8, #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)03191e3f5051inst 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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571630029025801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039
80204200381500029025801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039
80204200381500050025801081008000810080020500640132200192003820038997769989801202008003220080032201172003811802011009910010080000100000111511801600200350800001002003920039200392003920039
80204200381500029025801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801601200350800001002003920039200392003920039
80204200381500029025801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039
80204200381500029025801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039
802042003815000292002225801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039
80204200381500092025801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039
80204200381550029025801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039
8020420038150001071025801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3f51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004015000602580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100502017161662003580000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382011010005310018800102080000208000020038200381180021109101080000100502016166162003580000102003920039200392003920039
8002420038150001482580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100502016166132003580000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001005020161616162003580000102003920039200392003920039
80024200381612130392580010108000010800005064000002001920088202911003014101528049720802952080000200382003811800211091010800001005020161616162003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100502016166162003580000102003920039200392003920039
8002420038150001022580010108000010800005064000002006820038200389996310018800102080000208000020038200381180021109101080000100502016161662003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100502061616162003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100502016166162003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100502051616162003580000102003920039200392003920039