Apple M1 Microarchitecture Research by Dougall Johnson

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

TRN2 (vector, 2D)

Test 1: uops

Code:

  trn2 v0.2d, v0.2d, v1.2d
  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
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715246116872510001000100026468002018203720371572318951000100020002037203711100110000373116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000115226468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715010516872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715015616872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715010316872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  trn2 v0.2d, v0.2d, v1.2d
  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)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)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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000030012071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000027021071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000003071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768002001820037200371842231874510266200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100002400071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100002909071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100002506071011611197910100001002003820038200382003820038
1020420037150000012006119687641010010010012100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100001800071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100003002013071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa0a1a7a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000082196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000240064021622197850010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000030064021622197850010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000030064021622197850010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000030064021622197850010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  trn2 v0.2d, v1.2d, v0.2d
  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)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)9fa0a1a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000016819687251010010010000100100005002847680120018200372003718422318745101002001000020020332200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715000000025119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715000001206119687251010010010000100100005212847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000009071011611197910100001002003820038200382003820038
102042003715000000053619687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372017911102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010036100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038

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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010100640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150003881968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  trn2 v0.2d, v8.2d, v9.2d
  trn2 v1.2d, v8.2d, v9.2d
  trn2 v2.2d, v8.2d, v9.2d
  trn2 v3.2d, v8.2d, v9.2d
  trn2 v4.2d, v8.2d, v9.2d
  trn2 v5.2d, v8.2d, v9.2d
  trn2 v6.2d, v8.2d, v9.2d
  trn2 v7.2d, v8.2d, v9.2d
  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)03081e3f51inst 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)9fa6a8a9cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591510040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102161220035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102161120035800001002003920039200392003920039
802042003815000801258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102161120035800001002003920039200392003920039
802042003815000149258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101162120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038201891180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000610258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051341161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e3f51inst 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)9fa8acc2cfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500398125800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000050200416242003580000102003920039200392003920039
8002420038150003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000050200216242003580000102003920039200392003920039
8002420038150003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000250200216242003580000102003920039200392003920039
80024200381500039258001010800001080000506400002001920038200381000431001880010208000020160000200382003811800211091010800001000050200216422003580000102003920039200392003920039
8002420038150003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001003050200416342003580000102003920039200392003920039
80024200381500041925800101080000108000050640000200192003820038999631001880107208000020160000200382003811800211091010800001003050200416242003580000102003920039200392003920039
80024200381500123925800101080000108000050640000200192003820038999631001880010208009920160000200382003811800211091010800001000050200526422003580000102003920039200392003920039
80024200381500123925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000050200216422003580000102003920039200392003920039
8002420038150003925800101080000108000050640000201352003820038999631001880010208000020160000200382003811800211091010800001010050200416662003580000102003920039200392003920039
8002420038150008125800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000050200416422003580000102003920039200392003920039