Apple M1 Microarchitecture Research by Dougall Johnson

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

UHADD (vector, 16B)

Test 1: uops

Code:

  uhadd 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
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
100420371509616872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000373116111787100020382038203820382038
100420371508216872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uhadd 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)03080b1e1f3f4e51inst 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000107102162219791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100200067102162219791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100002007102162219791100001002003820038200382003820038
1020420037150006072619687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
102042003715500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000107102162219791100001002003820038200382003820038
1020420037150001206119687251010010010000100100005222847680020018200372003718422318745101002001000020020000200372003721102011009910010010000100000107102162219791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000207102162219791100001002003820038200382003820038
1020420037150000029119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090a0b18191e1f3f4e51inst 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)9fa1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000000888196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382008120038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000000861196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000906402162219785010000102003820038200382003820038
100242003715000000000986196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000000805196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000000996196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000000995196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uhadd 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)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)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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150851196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715011571968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010002497101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119794100001002003820038200382003820038
1020420037150166196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010002407101161119791100001002003820038200382003820038
1020420037150839196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150839196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010001107101161119791100001002008620038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03191e1f3a3f4e51inst 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)9fa8a9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003714900006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000104000640316331978510000102003820038200382003820038
1002420037150000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001016000640316331978510000102003820038200382003820038
100242003715000008219687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640316331978510000102003820038200382003820038
10024200371500000111019687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640316331978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640316331978510000102003820038200382003820038
10024200371500000166119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000101000640316331978510000102003820038200382003820038
1002420037150000020919687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640316331978510000102003820038200382003820038
1002420037150000072619687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640316331978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640316331978510000102003820038200382003820038
1002420037150000078619687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640316331978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uhadd v0.16b, v8.16b, v9.16b
  uhadd v1.16b, v8.16b, v9.16b
  uhadd v2.16b, v8.16b, v9.16b
  uhadd v3.16b, v8.16b, v9.16b
  uhadd v4.16b, v8.16b, v9.16b
  uhadd v5.16b, v8.16b, v9.16b
  uhadd v6.16b, v8.16b, v9.16b
  uhadd 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)030918191e1f3f51inst 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042004815000000100925801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511021611200350800001002003920039200392003920039
80204200381501000040258010010080000100800005006400002001920038200389973199996801002008000020016000020038200381180201100991001008000010042030511011611200350800001002003920039200392003920039
8020420038150000004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
80204200891500000082525801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039201422003920039
802042003815000000773258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100002005110116112003519800001002003920039200392003920039
80204200381500000073325801001008000010080000520640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
802042003815000018068825801001008000010080000500640000200192003820038997339996801002008039320016000020038200381180201100991001008000010020000511011611200350800001002003920039200392003920039
80204200381500000014925801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
802042003815000000122625801001008000010080000500640000200192003820038997379996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039201902003920039
8020420038150000004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392023720039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e3f51inst 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)9fa8acc5cfd5d6d9ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048151001062258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000502061606820035080000102003920039200392003920039
8002420038150001253258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000502081608620035080000102003920039200392003920039
8002420038150001279258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000502071606820035180000102003920039200392003920098
8002420038150001212258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000502061606820035080000102003920039200392003920039
80024200381500011562580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020916061020035080000102003920039200392003920039
800242003815009171258001010800001080194506400002001920088200389996310018800102080000201600002003820038118002110910108000010000502091608620035080000102003920039200392003920039
8002420038150001462258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000502081608620035080000102003920039200392003920039
80024200381500010982580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020816061020035080000102003920039200392003920039
80024200381500019025800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000050206160101020035080000102003920039200392003920039
8002420038150001155258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000502091608920035080000102003920039200392003920039