Apple M1 Microarchitecture Research by Dougall Johnson

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

SHLL2 (vector, 2D)

Test 1: uops

Code:

  shll2 v0.2d, v0.4s, #32
  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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371500821686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  shll2 v0.2d, v0.4s, #32
  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)03191e3f4e51inst 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)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150001098196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000938196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010010007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010010007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000170196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000168196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500082196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010030007101161119791100001002003820038200382003820038
102042003715000124196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200841110201100991001001000010002307101161119791100001002013320038200382003820038
1020420037150015828196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03183f4e51inst 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)9fa6a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150094719686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371500138919686251001010100001010000502847521020018200372003718443318785100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371500106919686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
1002420037149212819686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
1002420037150019119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000102013640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100020640216221978610000102003820038200382003820038
1002420037150062019686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
1002420037150023319686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  shll2 v0.2d, v8.4s, #32
  shll2 v1.2d, v8.4s, #32
  shll2 v2.2d, v8.4s, #32
  shll2 v3.2d, v8.4s, #32
  shll2 v4.2d, v8.4s, #32
  shll2 v5.2d, v8.4s, #32
  shll2 v6.2d, v8.4s, #32
  shll2 v7.2d, v8.4s, #32
  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)031e3f51inst 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)9fa6a8c5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815007125801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
8020420038150069425801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815009225801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815005225801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401322001920038200389977610023801202008003220080032200382003811802011009910010080000100001115118116020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815005225801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039

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)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)9fa0a1a6a8a9acc2cfd2d5d6dadbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150000000001042580010108000010800005064000001200190200382003899963100188001020800002080000200382003811800211091010800001000000005020013160011620035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000120019020038200389996310018800102080000208000020038200381180021109101080000100000000502006160010420035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000120019020038200389996310018800102080000208000020038200381180021109101080000100000000502007160010520035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000120019020038200389996310018800102080000208000020038200381180021109101080000100000000502004160010520035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000012001902003820038999631001880010208000020800002003820038118002110910108000010000000050200616009420035080000102003920039200392003920039
80024200381500000000010225800101080000108000050640000012001902003820038999631001880010208000020800002003820038118002110910108000010000000050200816006720035080000102003920039200392003920039
8002420038150000000002962580010108000010800005064000001200190200382003899963100188001020800002080000200382003811800211091010800001000026030502004160015420035080000102003920039200392003920039
80024200381500000000047525800101080000108000050640000012001902003820038999631001880010208000020800002003820038118002110910108000010000000050200416007420035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000012001902003820038999631001880010208000020800002003820038118002110910108000010000000050200616009420035080000102003920039200392003920039
80024200381500000000019225800101080000108000050640000012001902003820038999631001880010208000020800002003820038118002110910108000010000000050200616005620035080000102003920039200392003920039