Apple M1 Microarchitecture Research by Dougall Johnson

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

SADDW2 (vector, 4S)

Test 1: uops

Code:

  saddw2 v0.4s, v0.4s, v1.8h
  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)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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037160611687251000100010002646801205420372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371601661687251000100010002646801201820372037157231895100010002000203720371110011000173116111787100020382038203820382038
10042037166611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110001473116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000373116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  saddw2 v0.4s, v0.4s, v1.8h
  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)6061696d6edispatch 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)9fa0a1a6a8a9accfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000000611968725101001001000010010000500284768015200182003720037184223187451010020010000200200002003720037411020110099100100100001000000007105111611197910100001002003820038200382003820038
10204200371500000001721968725101001001000010010000500284768015200542003720037184223187451010020010000200200002003720037111020110099100100100001000000007105111611197910100001002003820038200382003820038
102042003715000000020819687251010010010000100100005002847680152001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071051116111979119100001002003820085200382007520038
102042021815011000034161961015410209100100001001106471628476801520018200372003718422271874511202224110032222099020371203708110201100991001001000010000000071051116111979123100001002037220375203732037320370
10204203261530073180291519632140101781001007213810456702285537815201622027820133184432618837107412181082921621992202742027751102011009910010010000100200021189381351256111996927100001002022920276203272027720276
10204202741521155795440611968725101001001000010010000500284768015200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007815111611197910100001002003820038200382003820038
10204200371500000002981968725101001001000010010000500284768015200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007105111611197910100001002003820038200382003820038
1020420037150000054306171968725101001001000010010000500284768015200182003720037184223187451010020010000200200002003720037111020110099100100100001000200007105111612197910100001002003820228200382003820038
10204200371500166672528354619687251010010010000100100005002847680102023520369203251844029188581104722410996224219882032520312711020110099100100100001002030207105111611197910100001002003820038200382003820038
10204200371500000001281968725101001001000010010000500284768015200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007105111611197910100001002003820038200382003820038

1000 unrolls and 10 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715001911968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003714908271968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715006119687251001010100001310000552847680120018200372003718444318767100102010000202000020037200371110021109101010000101500640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010600640217221978510000102003820038200382003820038
100242003715092361968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715008551968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010400640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010600640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715007021968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  saddw2 v0.4s, v1.4s, v0.8h
  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
1020420037150082119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100171507102161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150096019687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500769196872510100100100001001000050028476801200182003720037184222618745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010022247101161119791100001002003820038200382003820038
10204200371500887196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001002507101161119791100001002003820038200382003820038

1000 unrolls and 10 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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500191196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010106402162219785010000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500170196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200841500124196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010506402162219785010000102003820038200382003820038
10024200371500191196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715001259196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010066402162219785010000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010406402162219785010000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  saddw2 v0.4s, v8.4s, v9.8h
  saddw2 v1.4s, v8.4s, v9.8h
  saddw2 v2.4s, v8.4s, v9.8h
  saddw2 v3.4s, v8.4s, v9.8h
  saddw2 v4.4s, v8.4s, v9.8h
  saddw2 v5.4s, v8.4s, v9.8h
  saddw2 v6.4s, v8.4s, v9.8h
  saddw2 v7.4s, v8.4s, v9.8h
  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)0304080b1e3a3f51inst 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)9fa1a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150000024125801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511461699200350800001002003920039200392003920039
8020420038150000024125801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511491699200350800001002003920039200392003920039
80204200381500000210625801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010003000511491699200350800001002003920039200392003920039
80204200381500000257925801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511491699200350800001002003920039200392003920039
802042003815000002104258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000005114916992003523800001002003920039200392003920039
802042003815001002344258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000005114101677200350800001002003920039200392003920039
8020420038150000024125801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511491677200350800001002003920039200392003920039
80204200381500000215025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010001000511491699200350800001002003920039200392003920039
80204200381500000210425801001008008410080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000060511491699200350800001002003920039200392003920039
802042003815000002156325801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511491699200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080a18191e1f3f51inst 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004715000000060258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000050205163520035080000102003920039200392003920039
800242003815000000039258010410800941280000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050205165320035080000102003920039200392003920039
8002420038150000000104258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800221091010800001000000050205165320035080000102003920039200392003920039
800242003815000000060258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050205163520035080000102003920039200392003920039
8002420038150000000144258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050205165320035080000102003920039200392003920039
8002420038150000000169258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050203165320035080000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000110050203165520035080000102003920039200392003920039
8002420038150000000485258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050203165320035080000102003920039200392003920039
800242003815000000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000006050205165520035080000102003920039200392003920039
80024200381500000001123258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000003050205163520035080000102003920039200392003920039