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, 2S)

Test 1: uops

Code:

  urhadd 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)03081e3f4e51inst 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
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203716036116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110002073216221787100020382038203820382038
100420371502496116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  urhadd 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)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000012419687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715000000008419687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000052519687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000010319687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000168006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100200000071011611197910100001002003820038200382003820038
10204200371500000510084196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000005100071011611197910100001002003820038200382003820038
1020420037149000000040419687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037149000000041419687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308093f4e51inst 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
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001030640316331978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
100242003714900441196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001010640316331978510000102003820038200382003820038
100242003715001611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010240640316331978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001051183640316331978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
100242003715010611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010018640316331978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001010640316331978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  urhadd 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)03080b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680200182003720086184223187451010020010000200200002003720037111020110099100100100001000000000171011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000008419687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038

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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000190196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001002064041622197850310000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000064021622197850010000102003820038200382003820038
100242003715000317196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000064021622197850010000102003820038200382003820038
10024200371500082196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000064021622197850010000102003820038200382003820038
100242003715000105196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000064021622197850010000102003820038200382003820038
100242003715000172196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000064021622197850010000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000064021622197850010000102003820038200382003820038
100242003715000124196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000064021622197850010000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000064021622197850010000102003820038200382003820038
10024200371500061196872510010101001210100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000064021622197850010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  urhadd v0.2s, v8.2s, v9.2s
  urhadd v1.2s, v8.2s, v9.2s
  urhadd v2.2s, v8.2s, v9.2s
  urhadd v3.2s, v8.2s, v9.2s
  urhadd v4.2s, v8.2s, v9.2s
  urhadd v5.2s, v8.2s, v9.2s
  urhadd v6.2s, v8.2s, v9.2s
  urhadd 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)03080b18191e1f3f51inst 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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511041622200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511021622200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511021622200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511021622200350800001002003920039200392003920039
8020420038150000000114258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511021622200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511021622200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511021622200350800001002003920039200392003920039
802042003815000000082258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511021622200350800001002003920039200392003920039
8020420038150000000515258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511021622200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020087200381180201100991001008000010000000000511021622200350800001002003920039200392003920039

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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500165258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020316242003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005037416442003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020216342003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020716272003580000102003920039200392003920039
80024200381500392580010108000010800005064000012001920038201121000581004480010208000020160000200382003811800211091010800001005020316722003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020416642003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020216242003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020316442003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020216242003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020316422003580000102003920039200392003920039