Apple M1 Microarchitecture Research by Dougall Johnson

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

URHADD (vector, 4S)

Test 1: uops

Code:

  urhadd v0.4s, v0.4s, v1.4s
  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)033f4e51inst 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
1004203715611687251000100010002646801201820372037157231895100010002000203720371110011000073216111787100020382038203820382038
10042037152511687251000100010002646800201820372037157231895100010002000203720371110011000373116111787100020382038203820382038
10042037162101687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037152121687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203716611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  urhadd v0.4s, v0.4s, v1.4s
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007102161119791100001002003820038200382003820038
102042003715008419687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001005137101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150010519687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715008219687251010010010000100100005002847680120018200372003718422318745101002021000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715008219687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444818767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000001701968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444318767101642210168202032420084200852110021109101010000102202200506613242319878110000102008620084200862008620085
10024200851501111156885671967644100251110012101015255284896320054200852008418448818786101632010162202033820085200842110021109101010000102002203506612162219785010000102003820038200382003820038
100242003715000001501241968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  urhadd v0.4s, v1.4s, v0.4s
  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)0308090b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000710011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000710011611197910100001002003820038200382003820038
1020420037150000000008219687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000710011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000710011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000710011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680200182008520037184223187451010020010000200200002003720037111020110099100100100001000000000710011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000710011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000710011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000103100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000710011611197910100001002003820038200382003820038
1020420037150000000008219687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000710011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0309181e1f3f4e51inst 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)60696b6d6edispatch 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000061196872510010101000010100006028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500078082196872510010101000010100005028476800200650200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150000084196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100096402162219785610000102003820038200382003820038
1002420037150000061196872510010101000010100005028476800200180200372003718444818767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500000105196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006402162219834010000102003820038200382003820038
1002420037150000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500000191196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150000061196872510010101000010100005028476800200180200372008418444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  urhadd v0.4s, v8.4s, v9.4s
  urhadd v1.4s, v8.4s, v9.4s
  urhadd v2.4s, v8.4s, v9.4s
  urhadd v3.4s, v8.4s, v9.4s
  urhadd v4.4s, v8.4s, v9.4s
  urhadd v5.4s, v8.4s, v9.4s
  urhadd v6.4s, v8.4s, v9.4s
  urhadd v7.4s, v8.4s, v9.4s
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03091e3f51inst 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)60696b6d6edispatch 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060150048402580100100800001008000050064000012001902003820038997339996801002008000020016000020038200381180201100991001008000010000051102161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001902003820038997339996801002008000020016000020038200381180201100991001008000010000051441161120035800001002003920039200392003920039
8020420038150002402580100100800001008000050064000002001902003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001902003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001902003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
8020420038150039402580100100800001008000050064000002001902003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001902003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001902003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001902003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001902003820038997339996801002008000020016000020038200381180201100991001008000010009051101161120035800001002003920095200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)033f51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200471503925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
80024200381503925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
80024200381503925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
80024200381503925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
80024200381503925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
80024200381503925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
80024200381503925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
80024200381503925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
80024200381503925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
80024200381503925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039