Apple M1 Microarchitecture Research by Dougall Johnson

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

SSHLL2 (2D)

Test 1: uops

Code:

  sshll2 v0.2d, v0.4s, #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)0318191e1f3f4e51inst 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
10042037150000611686251000100010002645212018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
10042037150060611686251000100010002645212018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
10042037150096611686251000100010002645212018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
10042037150060821686251000100010002645212018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
10042037150000611686251000100010002645212018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
10042037150000611686251000100010002645212018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371500001271686251000100010002645212018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
10042037150000611686251000100010002645212018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371500270611686251000100010002645212018203720371571318951000100010002037203711100110001073216221786100020382038203820382038
10042037150000611686251000100010002645212018203720371571318951000100010002037203711100110000073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  sshll2 v0.2d, v0.4s, #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)03080b18191e1f3f4e51inst 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)9fa0a7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500000001241968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100001037101161119791100001002003820038200382003820038
10204200371500000301031968625101001001000010010000500284752120018200372003718421318745101002001000020010000201802003711102011009910010010000100001007101161119791100001002003820038200382003820038
1020420037150000012085219686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001001400007101161119791100001002003820038200382003820038
10204200371500000006119686251010010010000100100005002847521200182003720037184211718745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100001007101161119791100001002003820038200382003820038
1020420037150000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500000003461968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000061196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000003390251196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000000192061196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000010061196862510010101000010100005028475212001820037200371844303187671001022100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820084200371844303187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000006061196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150001000061196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sshll2 v0.2d, v8.4s, #3
  sshll2 v1.2d, v8.4s, #3
  sshll2 v2.2d, v8.4s, #3
  sshll2 v3.2d, v8.4s, #3
  sshll2 v4.2d, v8.4s, #3
  sshll2 v5.2d, v8.4s, #3
  sshll2 v6.2d, v8.4s, #3
  sshll2 v7.2d, v8.4s, #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)03070a0b1e3f51inst 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
80204200591501100292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151183165320035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013202001920038200389977699898012020080130200800322003820038118020110099100100800001000011151185163420035800001002003920039200392003920039
802042003815011012292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000311151185165420035800001002003920039200392003920039
802042003815011006942580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001009311151184164420035800001002003920092200932003920039
802042003815011027292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151185165520035800001002003920039200392003920039
802042003815011002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010001211151186165420035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151184166520035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000911151185163420035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151184174420035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151184164420035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a1e1f3a3f51inst 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)9fa9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501501112024625800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000502414161692003580000102003920039200392003920039
80024200381501100246258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005024151619162003580000102003920039200392003920039
80024200381501100246258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005024171619192003580000102003920039200392003920039
80024200381501100246258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005024171620172003580000102003920039200392003920039
80024200381501100246258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005024151616162003580000102003920039202382003920039
800242003815011150246258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005024171617172003580000102003920039200392003920039
80024200381501100246258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005024171617172003580000102003920039200392003920039
80024200381501100246258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005024191615162003580000102003920039200392003920039
80024200381501100246258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005024171617172003580000102003920039200392003920039
80024200381501100246258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005024171615172003580000102003920039200392003920039