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, 16B)

Test 1: uops

Code:

  urhadd 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)0318191e3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203716000611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150003001687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715000611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150002991687251000100010002646802018203720371572318951000100020002037203711100110000373216221787100020382038203820382038
10042037150012611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715000611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203716000611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715000611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715000611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150012611687251000100010002646802018203720371572318951000100020002037203711100110000373216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  urhadd 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)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)9fa0a8a9acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000009007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001071000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000138007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010456500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010003806007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000300007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001015007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b18191e1f3f4e51inst 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)72scheduler 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)9fa0a1a7a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100221091010100001000065030064031633197850010000102003820038200382003820038
10024200371490000061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100000030064031633197850010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100000000064031633197850010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000000150064031633197850010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100000004064031633197850010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100000030064031633197850010000102003820038200382003820038
10024200371500001860631196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100000000064031633197850010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000000330064031633197850010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100002030064031633197850010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476801200182003720179184440318767100102010000202000020037200371110021109101010000100000000064031633197850010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  urhadd 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)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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001071011611197910100001002003820038200382003820038
102042003715000611968763101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284896302001820037200841842531874510100200100002002000020084200371110201100991001001000010000071011611197910100001002008520038200382003820038
1020420037150792440352019599138102281411007213611064643285666112023420370202271844733188741088422411158224216662035820370711020110099100100100001002013915877172222004129100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080a0b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150101000002681968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006441016101019785010000102003820038200382003820038
1002420037150101000002681968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000010306441016101019785010000102003820038200382003820038
1002420037150101000002681968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000020006441016111019785010000102003820038200382003820038
100242003715010100000289196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000000644101610519785010000102003820038200382003820038
100242003715010100000268196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000000644516101019785010000102003820038200382003820038
100242003715010100000268196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000000644101651019785010000102003820038200382003820038
1002420037150101000002681968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000010906441016101019785010000102003820038200382003820038
1002420037150101000002163196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000000644516101019785010000102003820038200382003820038
10024200371501010000026819687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000101206441016101119785010000102003820038200382003820038
1002420037150101000002681968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000040006441016101019785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  urhadd v0.16b, v8.16b, v9.16b
  urhadd v1.16b, v8.16b, v9.16b
  urhadd v2.16b, v8.16b, v9.16b
  urhadd v3.16b, v8.16b, v9.16b
  urhadd v4.16b, v8.16b, v9.16b
  urhadd v5.16b, v8.16b, v9.16b
  urhadd v6.16b, v8.16b, v9.16b
  urhadd 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)033f51inst 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)9fa0a1a6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420048150103258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000051102161120035800001002003920039200392003920039
802042003815040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161120035800001002003920039200392003920039
802042003815040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161120035800001002003920039200392003920039
802042003815040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000003051101161120035800001002003920039200392003920039
802042003815040458010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161120035800001002003920039200392003920039
8020420038150610258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161120035800001002003920039200392003920039
802042003815040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161120035800001002003920039200392003920039
802042003815040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161120035800001002003920039200392003920039
802042003815040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000003051101161120035800001002003920039200392003920039
802042003815040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000030051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050203161120035080000102003920039200392003920039
80024200381500392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000050201161120035080000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050201161120035080000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018801182080000201600002003820038118002110910108000010000350201161120035080000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050201161120035280000102003920039200392003920039
800242003815003142580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010202350201161120035080000102003920097201432003920096
800242003815001502580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010022350201161120035080000102003920039200392003920039
80024200381500602580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050201161120035080000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050201161120035080000102003920039200392003920039
800242003815001342580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050291161120035080000102003920039200392003920039