Apple M1 Microarchitecture Research by Dougall Johnson

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

TRN1 (vector, 16B)

Test 1: uops

Code:

  trn1 v0.16b, v0.16b, v1.16b
  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
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073216221823100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037161806116872510001000100026468002018203720371572318951000100020002037203711100110000079216221787100020382038203820382038
1004203715010316872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371766116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  trn1 v0.16b, v0.16b, v1.16b
  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)031e1f3f4e51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510277200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
10204200371502730611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715060611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000107102162219791100001002017020373202752008520038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038

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)9fa8c2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037155061196672510010101000010100005028476802001820037200371845531876710010201000020200002003720037111002110910101000010006404163419785010000102003820038200382003820038
10024200371504561196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010006403164419785010000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010006404163419785010000102003820038200382003820038
1002420037150661196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010006404164419785010000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010006404164319785010000102003820038200382003820038
10024200371500346196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010006403164419785010000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010406404164419785010000102003820038200382003820038
100242003715013261196872510010101001210100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010006404163419785010000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010006404164419785010000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010006404163419785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  trn1 v0.16b, v1.16b, v0.16b
  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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000000006119687251010010010000100100005002847680200182003720037184223187451034020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000008219687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000015006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000025119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000073512511197910100001002003820038200382003820038
10204200371500000000010319687251010010010000100100005002847680200902003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b18191e1f3f4e51inst 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)9fa0a1a6a8a9accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100001000640216221978510000102003820038200382003820038
1002420037151000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020131200371110021109101010000100000000640216221978510000102003820038200382003820038
1002420037150000006119687251001010100121010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000640216221978510000102003820038200382003820038
10024200371500001206119687251001010100001010000502847680020018200372003718444318767100102010000202000020037201791110021109101010000100000000640216221978510000102003820133200852008520038
1002420037150000006119687251001010100001010000502852812120018200372003718444318767100102010000202000020037200371110021109101010000100000060640216221978510000102003820038200382013320038
10024200371590003606119687251001010100121010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000640216221978510000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000059380640216221978510000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680020018200852003718444318767100102010000202000020037200371110021109101010000100000000640216221978510000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000640216221978510000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  trn1 v0.16b, v8.16b, v9.16b
  trn1 v1.16b, v8.16b, v9.16b
  trn1 v2.16b, v8.16b, v9.16b
  trn1 v3.16b, v8.16b, v9.16b
  trn1 v4.16b, v8.16b, v9.16b
  trn1 v5.16b, v8.16b, v9.16b
  trn1 v6.16b, v8.16b, v9.16b
  trn1 v7.16b, v8.16b, v9.16b
  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)030818191e1f3f51inst 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)9fa0a6a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200481500000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511021611200350800001002003920039200392003920039
80204200381550000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000003511011611200350800001002003920039200392003920039
80204200381510000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
802042003815000027040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
802042003815000000135258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
80204200381500000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
80204200381500000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000015511011611200350800001002003920039200392003920039
80204200381500000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
80204200381550000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070818191e1f3f51inst 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)5f60696d6edispatch 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)9fa1a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000000050203166620035080000102011020039200392011120039
80024200381500000120392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001000000050205166520035080000102003920039200392003920039
8002420038150000000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000000050376166420035080000102003920039200392003920039
8002420038150000000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000000050205165520035080000102003920039200392003920039
80024200381500000240392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000000050204166620035080000102003920039200392003920039
8002420038150000000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000003050204167420035080000102003920039200392003920039
8002420038150000000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000000050205164620035080000102003920039200392003920039
8002420038155000000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000000050205164420035080000102003920039200392003920039
8002420038150000000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000000050205165420035080000102003920039200392003920039
80024200381500000240392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000000050205165520035080000102003920039200392003920039