Apple M1 Microarchitecture Research by Dougall Johnson

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

SSHLL2 (4S)

Test 1: uops

Code:

  sshll2 v0.4s, v0.8h, #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)6061696d6edispatch 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)a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150611686251000100010002645210020182037203715713189510001000100020372037111001100000730116111786100020382038203820382038
10042037150611686251000100010002645210020182037203715713189510001000100020372037111001100060730116111786100020382038203820382038
10042037150611686251000100010002645210020182037203715713189510821000100020372037111001100000730116111786100020382038203820382038
10042037150611686251000100010002645210020182037203715713189510001000100020372037111001100010730116111786100020382038203820382038
10042037150611686251000100010002645210020182037203715713189510001000100020372037111001100000730116111786100020382038203820382038
10042037150611686251000100010002645210020182037203715713189510001000100020372037111001100000730116111786100020382038203820382038
10042037150821686251000100010002645210020182037203715713189510001000100020372037111001100000730116111786100020382038203820382038
10042037160611686251000100010002645211020182037203715713189510001000100020372037111001100000730116111786100020382038203820382038
10042037150821686251000100010002645210020182037203715713189510001000100020372037111001100010730116111786100020382038203820382038
100420371501031686251000100010002645210020182037203715713189510001000100020372037111001100000730116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  sshll2 v0.4s, v0.8h, #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)031e1f3f4e51inst 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)9fa0a1a6a8cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371501506119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820084
1020420037149006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150306119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150906119675251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150306119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150606119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150101015688061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000000103196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000306402162219786010000102003820038200382003820038
10024200371500000120061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000010006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475211200182008520037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000000551196862510010101000010100005028475211202702041320463184755018946106212611516261151720416204501111002110910101000010203021601008385803220133410000102046720414201342003820038
100242003715500001056616134341960917810110131009616112167128575571202702041720464184653718915113862411506201100620368205111011002110910101000010422121792008181903220020310000102051420452204172042020464
100242050815900661188880025211958720310051121009614112168128563690202702035720369184683318913104692411276241134720497205101111002110910101000010020101962508403892320110410000102050220547205602050020512
10024200371550010109244400431819609183101201510084191136888285889712030620464200831847647189411149920109972811512204632032311110021109101010000102001419805284741052320129010000102003820038201332003820512
1002420323158012813244006119598120100981110048101000050284752102034220275203681846240188521062024111812010594203192017871100211091010100001000000795506402162219786010000102003820038200382003820038
1002420037155000000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sshll2 v0.4s, v8.8h, #3
  sshll2 v1.4s, v8.8h, #3
  sshll2 v2.4s, v8.8h, #3
  sshll2 v3.4s, v8.8h, #3
  sshll2 v4.4s, v8.8h, #3
  sshll2 v5.4s, v8.8h, #3
  sshll2 v6.4s, v8.8h, #3
  sshll2 v7.4s, v8.8h, #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)0307080a0b181e3f51inst 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)9fa0a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715011011029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
8020420038150101001871258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
802042003815010100029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
802042003815010100029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000311151181161120035800001002009120096200392003920039
80204200381511010054029508010810080008100800205006401321200582003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
802042003815010100029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
8020420038150101001229258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
802042003815010100071258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
802042003815010100029258010810080076100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002024420039200392003920039
802042003815010101329258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3f51inst 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)5f60696d6edispatch 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)9fa9acc2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401503000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000502001216742003580000102003920039200392003920039
800242003815000003925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100005020051612112003580000102003920039200392003920039
80024200381500012039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000050200616742003580000102003920039200392003920039
800242003815000003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100005020011161162003580000102003920039200392003920039
80024200381550000252258001010800001080124506400000120019200382003899963100188001020800002080000200382003811800211091010800001000050200616652003580000102003920039200392003920039
8002420038149000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000050200616542003580000102003920039200392003920039
8002420038150000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000050200616492003580000102003920039200392003920039
8002420038150000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000050200616652003580000102003920039200392003920039
8002420038150000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000050200916542003580000102003920039200392003920039
800242003815000003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100005020051611102003580000102003920039200392003920039