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, 8H)

Test 1: uops

Code:

  trn1 v0.8h, v0.8h, 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)033f4e51inst 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
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037156116874810001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037158216872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037166116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110001073216221787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  trn1 v0.8h, v0.8h, 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)03181e3f4e51inst 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)9fa8c3cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715002461196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200841500061196872510100100100121001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715002461196672510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150038461196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150036061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715005461196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715002761196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119861100001002003820038200382003820038

1000 unrolls and 10 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)9fa1a8acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715024061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000682316331978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640316331978510000102003820038200382003820038
100242003715000726196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640316331978510000102003820038200382003820038
1002420037150255061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640316331978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640316331978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640316331978510000102003820038200382003820038
1002420037150002023196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640316331978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640316331978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640316331978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640316331978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  trn1 v0.8h, v1.8h, 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)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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371490000011704411968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000002000071011611197910100001002003820038200382003820038
1020420037150000001020611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000090891968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000090611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000000000071041611197910100001002003820038200382003820038
1020420037150000002610611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000891968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000000540611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03081e3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500336119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000640416221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640424221978510000102003820038200382003820038
1002420037150036119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150024060519687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150096119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242018115003756119687251001010100361010000502847680020018020037200371844431876710621201000020203382008520037111002110910101000010130640216221978510000102003820038200382003820038
100242003715013914919687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010131640216221978510000102003820038200382003820038
10024200371500156119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  trn1 v0.8h, v8.8h, v9.8h
  trn1 v1.8h, v8.8h, v9.8h
  trn1 v2.8h, v8.8h, v9.8h
  trn1 v3.8h, v8.8h, v9.8h
  trn1 v4.8h, v8.8h, v9.8h
  trn1 v5.8h, v8.8h, v9.8h
  trn1 v6.8h, v8.8h, v9.8h
  trn1 v7.8h, v8.8h, 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)03080b1e1f3f51inst 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)9fa6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000270402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000051102161120035800001002003920039200392003920039
802042003815000180402580215100800001088000050064000012001920038200389973399968010020080000200160000200382003821802011009910010080000100000000051101161120035800001002003920039200392003920039
80204200381500000402580100100800001008000050064000002001920038200389973399968010020080000202160000200382003811802011009910010080000100000000051101161120035800001002003920039200392003920039
80204200381500000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000051101161120035800001002003920039200392003920039
80204200381500000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000051101161120035800001002003920039200392003920039
80204200381500000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000051102171120035800001002003920039200392003920039
80204200381500000404880100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000051101161120035800001002003920039200392003920039
80204200381501000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000051101161120035800001002003920039200392003920039
802042003815600004602580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000051101161120035800001002003920039200392003920039
80204200381500000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100010000051101161220035800001002003920039200392003920039

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)696b6d6edispatch 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)9fa0a6a8acc2cfd5d6dbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815502439258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001000000502031603320035080000102003920039200392003920039
80024200381500039258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001000000502031604320035080000102003920039200392003920039
800242003815002439258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001000000502021603320035080000102003920039200392003920039
80024200381500039258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001000000502031602320035080000102003920039200392003920039
80024200381550039258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001000000502031603320035080000102008920039200392003920039
800242003815001539258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001000000502031603220035080000102003920039200392003920039
80024200381500039258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001000000502021604320035080000102003920039200392003920039
800242003815006339258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001000000502021603320035080000102003920039200392003920039
80024200381500039258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001000000502031603320035080000102003920039200392003920039
80024200381500039258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001000000502031604320035080000102003920039200392003920039