Apple M1 Microarchitecture Research by Dougall Johnson

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

EOR3 (vector, 16B)

Test 1: uops

Code:

  eor3 v0.16b, v0.16b, v1.16b, v2.16b
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(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)03081e3f4e51inst 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
1004203715006116872510001000100026468012018203720371572318951000100030002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100030002037203711100110000073216221787100020382038203820382038
1004203715008416872510001000100026468012018203720371572318951000100030002037203711100110000073216221787100020382038203820382038
1004203716006116872510001000100026468012018203720371572318951000100030002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100030002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100030002037203711100110000073216221787100020382038203820382038
10042037150816116872510001000100026468012018203720371572318951000100030002037203711100110000073216221787100020382038203820382038
1004203715008216872510001000100026468012018203720371572318951000100030002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100030002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100030002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  eor3 v0.16b, v0.16b, v1.16b, v2.16b
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b18191e3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000241031964325101001001000010010000500284768012001820037200371842231874510100200100002003000020037200371110201100991001001000010000371021622197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002003000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002003000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
102042003715000001561968725101001001000010010000500284768012001820227200371842231874510100200100002003000020037200371110201100991001001000010000071021622197910100001002003820085200382008620038
10204201801500000611968725101001001000010010000500284768012001820037200371842231874510100200100002003000020037200371110201100991001001000010000071021623197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002003000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002003000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002003000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820085200371842231874510100200100002003000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002043000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010100640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000005361968725100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000001031967625100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010000640316221978510000102003820038200382003820038
10024200371491000611968725100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012009020037200371844431876710010201000020300002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  eor3 v0.16b, v1.16b, v0.16b, v2.16b
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3a3f4e51inst 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)9fa8accdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000611968725101001001000010010000500284768002001820133200371842231874510100200100002003000020037200371110201100991001001000010000071003162219791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002003000020037200371110201100991001001000010000071002162219791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002003000020037200371110201100991001001000010000071002162219791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002003000020037200371110201100991001001000010000071002162219791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002003000020037200371110201100991001001000010000071002162219791100001002003820038200382003820038
1020420037150600611968725101001001000010010000500284768012001820037200371842231874510100200100002003000020037200371110201100991001001000010000071014162219791100001002003820038200382003820038
102042003715054003461968725101001001000010010000500284768002001820037200371842231874510100200100002003000020037200371110201100991001001000010000071012162319791100001002003820038200382003820038
102042003715040500611968725101001001000010010000500284768002001820037200371842231874510100200100002003000020037200371110201100991001001000010000071012162219791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002003000020037200371110201100991001001000010000071012162219791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002003000020037200371110201100991001001000010000071012162219791100001002003820038200382003820038

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)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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000006119687251001010100001010000502847680120018020037200371844431878810010201000020300002003720037111002110910101000010000000006402162319785010000102003820038200382003820038
10024200371500000381006119687251001010100001010000502847680120018020084200371844431878610010201000020300002003720037111002110910101000010000000006402162219785010000102003820085200382003820038
100242003715000000006119687251001010100001010000502847680120018020037200371844431876710010201000020300002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680120018020037200371844431876710010201000020300002003720037111002110910101000010000000006403163219785010000102003820038200382003820038
100242003715000006006119687251001010100001010000502847680120018020037200371844431876710010201000020300002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000008919687251001010100001010000502847680120018020037200371844431876710010201000020300002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680120018020037200371844431880310162201000020300002003720037111002110910101000010000000006403162219785010000102003820038200382003820038
1002420037150000027006119687251001010100001010000502847680120018020037200371844431876710010201000020300002003720037211002110910101000010000000006403162219785010000102003820038200382003820038
100242003715000006006119687251001010100001010000502847680120018020037200371844431876710010201000020300002003720037111002110910101000010000000006402163319785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200180200372003718444251876710010201000020300002003720037111002110910101000010000000006403162219785010000102003820038200382003820038

Test 4: Latency 1->4

Code:

  eor3 v0.16b, v1.16b, v2.16b, v0.16b
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e3a3f4e51inst 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)9fa0a1a8acc5cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000015019687251010010010000100100005002847680200182003720037184297187411010020010008200300242003720037111020110099100100100001000040171214162219791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000000071013162319791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000020071012162219791100001002003820038200382003820038
1020420037150000072619687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000010071012162219791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000000071012162219791100001002003820038200382003820038
102042003715000016119687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000030071012162219791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000010071012162219791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000000071012162219791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000030071012162219791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000020071012162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000203000020037200371110021109101010000100000640316221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000203000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003714900611968725100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010001620640216221978510000102003820038200382003820038
10024200371500025119687251001010100001010000502847680120018200372003718444318767100102010000203000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371500010319687251001010100001010000502847680120018200372003718444318767100102010000203000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000203000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000203000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000203000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000203000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000203000020037200371110021109101010000100000640216221978510000102003820038200382003820038

Test 5: throughput

Count: 8

Code:

  eor3 v0.16b, v8.16b, v9.16b, v10.16b
  eor3 v1.16b, v8.16b, v9.16b, v10.16b
  eor3 v2.16b, v8.16b, v9.16b, v10.16b
  eor3 v3.16b, v8.16b, v9.16b, v10.16b
  eor3 v4.16b, v8.16b, v9.16b, v10.16b
  eor3 v5.16b, v8.16b, v9.16b, v10.16b
  eor3 v6.16b, v8.16b, v9.16b, v10.16b
  eor3 v7.16b, v8.16b, v9.16b, v10.16b
  movi v8.16b, 9
  movi v9.16b, 10
  movi v10.16b, 11

(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)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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002002400002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002002400002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002002400002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002002400002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002002400002003820038118020110099100100800001000651101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002002400002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002002400002003820038118020110099100100800001000651101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002002400002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002002400002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815015402580100100800001008000050064000020019200382003899733999680100200800002002400002003820038118020110099100100800001002051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307090a0b18191e1f3a3f51inst 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)9fa0a1a6a8a9acc2cfd0d2d5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000000900392580010108000010800005064000010200192003820038999631001880010208000020240000200382003811800211091010800001000000005020532716015252003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000010200192003820038999631001880010208000020240000200382003811800211091010800001000000005020532116026192003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000005200192003820038999631001880010208000020240000200382003811800211091010800001000000005020002516024242003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000010200192003820038999631001880010208000020240000200382003811800211091010800001000000005020001916326132003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000005200192003820038999631001880010208000020240000200382003811800211091010800001000000005020541916025132003580000102003920039200392003920039
8002420038150000000000392580286108000010800005064000010200192003820038999631001880010208000020240000200382003811800211091010800001000000005020002516019262003580000102003920039200392003920039
8002420038150001000000392580010108000010800005064000005200192003820038999631001880010208000020240000200382003811800211091010800001000000005020542516015242003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000015200192003820038999631001880010208000020240000200382003811800211091010800001000000005020542516023232003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000005200692003820038999631001880010208000020240000200382003811800211091010800001000000005020002516016262003580000102003920039200392003920039
8002420038150000000000392580010108000010800006264000015200192003820038999631001880010208000020240000200382003811800211091010800001000000005020541316023202003580000102003920039200392003920039