Apple M1 Microarchitecture Research by Dougall Johnson

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

URHADD (vector, 8H)

Test 1: uops

Code:

  urhadd 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)03181e3f4e51inst 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
10042037160126116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203716006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203716006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000373116111787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116112034100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203716006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  urhadd 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)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)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)9fa0accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007102161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371501094319687251010010010000100101525002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

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)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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000000061196872510010101000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
100242003715000000000726196872510010101000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000090061196872510010101000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000100001006402162219785010000102003820038200382003820038
100242003715000000600726196872510010101000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
100242003715000000210061196872510010101000010100005028476801020018200372003718444318767101652010000202000020037200371110021109101010000104200461957516482319967210000102027420227200852032120275
1002420274152010556634401256019632100100621410060161076098285281210201982022820131184612118842106222010827222201220274202766110021109101010000102200282037263575219967310000102027420276202752022720171

Test 3: Latency 1->3

Code:

  urhadd 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)033f4e51inst 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
10204200371506119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001002537101161119791100001002003820038200382003820038
10204202271506119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001001007101161119791100001002003820038200382003820038
10204200371506119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001002707101161119791100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100537101161119791100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

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)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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001045640416341978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001021640316431978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640416431978510000102003820038200382003820038
100242003714901561196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001021640416441978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640316441978510000102003820038200382003820038
1002420037150106119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640316341978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001021640416431978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318771100102010000202000020037200371110021109101010000100640416441978510000102003820038200382003820038
1002420037150006619687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640416441978510000102003820038200382003820038
1002420037149006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640416341978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  urhadd v0.8h, v8.8h, v9.8h
  urhadd v1.8h, v8.8h, v9.8h
  urhadd v2.8h, v8.8h, v9.8h
  urhadd v3.8h, v8.8h, v9.8h
  urhadd v4.8h, v8.8h, v9.8h
  urhadd v5.8h, v8.8h, v9.8h
  urhadd v6.8h, v8.8h, v9.8h
  urhadd 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)030b1e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051104162220035800001002003920039200392003920039
80204200381550023025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001003351102162220035800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100018051102162220035800001002003920039200392003920039
80204200381501040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010036351102162220035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010010351102162220035800001002003920039200392003920039
8020420137150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001004351102162220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e3f51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004715000039258001210800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000103101085020516632003580000102003920039200392003920039
800242003815000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100095020716342003580000102003920039200392003920039
8002420038149029395180010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001023205020716472003580000102003920039200392003920039
800242003815000039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000103001655020316342003580000102003920039200392003920039
800242003815000039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100005020416672003580000102003920039200392003920039
800242003815000039258001010800001080000506400001020019200382003899963100188001020800002016000020038200381180021109101080000100065020416342003580000102003920039200392003920039
800242003815000039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000102005020416442003580000102003920039200392003920039
800242003815000039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100005020716642003580000102003920039200392003920039
800242003815000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000103005020616432003580000102003920039200392003920039
800242003815000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100005020616442003580000102003920039200392003920039