Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHL (vector, 4H)

Test 1: uops

Code:

  sqshl v0.4h, v0.4h, v1.4h
  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
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshl v0.4h, v0.4h, v1.4h
  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)03080a0b18191e1f3f4e51inst 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
1020420037150000000095119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000003803071021622197910100001002003820038200382003820038
1020420037149000000053719687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820138
102042003715000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
10204200371500000000116819687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
1020420037150000000073519687251010010010000100100005002847680020018200372003718422318745101002001018020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000004503071021622197910100001002003820038200382003820038
1020420037150000000014719687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
102042003715000000006119687251010010010000107100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
102042003715000000006119687251010010010000106100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa1a6a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006403162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000106006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000008919687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000100006402162219785010000102003820038200382003820038
100242003715000000008219654136100701710060151091282285152920198202772027818466191885910773221082224203382032420311611002110910101000010421010300007472723319967210000102032320322203112032520086
10024203701520006679252830041962113810010151007212107606128553782023420367203201846630188351092720108322221988201802032371100211091010100001000000006402162219785010000102003820085202752022720274

Test 3: Latency 1->3

Code:

  sqshl v0.4h, v1.4h, v0.4h
  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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000000536196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000210061196876310100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011621197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000082196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000026019687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000055015071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000103196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000002011071011611197910100001002003820038200382003820038
1020420037150000000082196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000100071011611197910100001002003820038200382003820038
10204200371500000000107196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000322196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820085200382003820038

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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037185150731196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
100242003718500189196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
100242003718600189196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
100242003718500103196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
100242003717400189196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
10024200371730084196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
100242003717414717661196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
100242003717300251196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
100242003716100103196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001013640316331978510000102003820038200382003820038
10024200371600061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001010640316331978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  sqshl v0.4h, v8.4h, v9.4h
  sqshl v1.4h, v8.4h, v9.4h
  sqshl v2.4h, v8.4h, v9.4h
  sqshl v3.4h, v8.4h, v9.4h
  sqshl v4.4h, v8.4h, v9.4h
  sqshl v5.4h, v8.4h, v9.4h
  sqshl v6.4h, v8.4h, v9.4h
  sqshl v7.4h, v8.4h, v9.4h
  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)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)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
802042005815004532580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051103162220035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001002351102162220035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
80204200381509105258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100152751102162220035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
80204200381500822580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
80204200381500822580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
802042003815001242580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039

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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500148258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020516432003580000102003920039200392003920039
800242003815001126258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000105020316442003580000102003920039200392003920039
8002420038150062258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020416442003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020416442003580000102003920039200392003920039
8002420038150062258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020316432003580000102003920039200392003920039
8002420038150060258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020416432003580000102003920039200392003920039
8002420038150062258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020416432003580000102003920039200392003920039
80024200381500102258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020416432003580000102003920039200392003920039
80024200381500125258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020316342003580000102003920039200392003920039
80024200381500426258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020416432003580000102003920039200392003920039