Apple M1 Microarchitecture Research by Dougall Johnson

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

SRHADD (vector, 2S)

Test 1: uops

Code:

  srhadd v0.2s, v0.2s, v1.2s
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110002073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  srhadd v0.2s, v0.2s, v1.2s
  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)03081e1f3f4e51inst 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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100212100002002000020037200371110201100991001001000010027101161119791100001002003820038200382003820038
1020420037150000595196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150000251196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200841110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820084200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307081e3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640416551978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640516541978510000102003820038200382003820038
100242003715000213611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640616561978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010019680640616441978510000102003820038200382003820038
1002420037161000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640516551978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640516551978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640416451978510000102003820038200382003820038
1002420037186000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640516541978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640516651978510000102003820038200382003820038
1002420083150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640416451978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  srhadd v0.2s, v1.2s, v0.2s
  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)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)9fc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119687251010010010000100100005002847680120018200372003718429061874010100200100082002001620037200371110201100991001001000010011171811611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422031874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422031874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422031874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422031874510100204100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422031874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422031874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422031874510100200100002002000020037200371110201100991001001000010000073511611198590100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422031874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200852003718422031874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820086

1000 unrolls and 10 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)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
10024200371500000060061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006405162219785010000102003820038200382003820038
10024200371510000000086196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000120061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000001087196764310010101000010100005028476801200542003720037184573187671001024100002020000200372008511100211091010100001000010306402162219785010000102003820038200382003820038
100242003715000000000103196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000010306402162219785010000102003820038200382003820038
1002420037150000001200536196872510010101000010100005028476801201262003720037184443187671001020100002020000200372003711100211091010100001000200006402162219785110000102022720038200382003820038
10024200371500000012176061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10025200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000306402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  srhadd v0.2s, v8.2s, v9.2s
  srhadd v1.2s, v8.2s, v9.2s
  srhadd v2.2s, v8.2s, v9.2s
  srhadd v3.2s, v8.2s, v9.2s
  srhadd v4.2s, v8.2s, v9.2s
  srhadd v5.2s, v8.2s, v9.2s
  srhadd v6.2s, v8.2s, v9.2s
  srhadd v7.2s, v8.2s, v9.2s
  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)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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511021611200350800001002003920039200392003920039
80204200381500402580100100800001008010450064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100400511011611200350800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000005110116112003516800001002003920039200392003920039
8020420038150309402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815012402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039

1000 unrolls and 10 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020316352003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020316542003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019201352003899963100188001020800002016019820090200381180021109101080000100045020416442003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020416442003580000102003920039200392003920039
8002420038150246392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020516532003580000102003920039200392003920039
8002420038150432392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020316442003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020316522003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382008999963100188001020800002016000020038200381180021109101080000100005020416452003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020416432003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100305020516552003580000102003920039200392003920039