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, 2S)

Test 1: uops

Code:

  uhadd v0.2s, v0.2s, v1.2s
  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)696d6edispatch 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)a0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203716061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
10042037160130168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
100420371513261168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
10042037152161168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
10042037150128168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uhadd v0.2s, v0.2s, v1.2s
  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)0308090b3f4e51inst 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
10204200371490006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001447102162219791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001327102162219791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
10204200371500006119687251011510010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219855100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
10204200371490006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100067102162219791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038

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)9fa1a7a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003720200316196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000160640316331978510000102003820038200382003820038
100242003718600611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000870640316331978510000102003820038200382003820038
100242003718600611968725100101010000101000055284768002001820037200371844431876710010201000020200002003720037111002110910101000010000870640316331978510000102003820038200382003820038
1002420037173006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100001170640316331978510000102003820038200382003820038
10024200371740061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000030640316331978510000102003820038200382003820038
1002420037173006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100049960640316331978510000102003820038200382003820038
1002420037173012103196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000160640316331978510000102003820038200382003820038
100242003716101261196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640316331978510000102003820038200382003820038
10024200371610061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640316331978510000102003820038200382003820038
10024200371600061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000100640316331978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uhadd v0.2s, v1.2s, v0.2s
  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)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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968725101001001000010010000500284768012001820133200891842231874510100200100002002000020037200371110201100991001001000010001007102161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002133020037200371110201100991001001000010000007101161119791100001002003820038201332003820038
102042003715000611968725101001001000013310000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010006037101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000201692003711102011009910010010000100044037101161219791100001002003820038200382003820038
1020420037150001031968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000037101161119791100001002003820038200382008620038
1020420037150021611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010002037101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150048611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010002067101161119791100001002003820038200382003820038

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)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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010301640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100660640216221978510000102003820038200382003820038
100242003715002511968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010100640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038201312003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820181200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uhadd v0.2s, v8.2s, v9.2s
  uhadd v1.2s, v8.2s, v9.2s
  uhadd v2.2s, v8.2s, v9.2s
  uhadd v3.2s, v8.2s, v9.2s
  uhadd v4.2s, v8.2s, v9.2s
  uhadd v5.2s, v8.2s, v9.2s
  uhadd v6.2s, v8.2s, v9.2s
  uhadd v7.2s, v8.2s, v9.2s
  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)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)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)9fa8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420048150004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001004360511041622200350800001002003920039200392003920039
80204200381500032525801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001002760511021622200350800001002003920039200392003920039
802042003815000842580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511021622200350800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001002200511021622200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511021622200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511021622200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100360511021622200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511021622200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511021622200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511021623200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308181e3a3f51inst 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)9fa0a1a8a9accdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000502001616121120035080000102003920039200392003920039
8002420038150000039258001010800001080000506400000200192003820038999631004480010208000020160000200382003811800211091010800001000000050200716121120035080000102003920039200392003920039
8002420038150000081258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050200121612720035080000102003920039200392003920039
800242003815000001232580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000502001116111220035080000102003920039200392003920039
800242003815000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100010005020091611920035080000102003920039200392003920039
800242003815000001232580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000502001116121020035080000102003920039200392003920039
80024200381500000392580010108000010800005064000002001920038200989996310018800102080000201600002003820038118002110910108000010001030502001216141020035080000102003920039200392003920039
8002420038150000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050200121610620035080000102003920039200392003920039
80024200381500000102258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050200101611820035080000102003920039200392003920039
8002420038150000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050200121612720035080000102003920039200392003920039