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, 8H)

Test 1: uops

Code:

  sqshl v0.8h, v0.8h, v1.8h
  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)a1a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150821687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150821687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371501031687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150821687251000100010002646802018203720371572318951000100020002037203711100110000073116111809100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715121201687251000100010002646802018203720371572318951000100020002037203711100110000173116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshl v0.8h, v0.8h, v1.8h
  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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500000000166196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000000082196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037149000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031f3a3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150026219687251001010100001010000502847680020018200372003718444318767101272010000202000020037200371110021109101010000100006441016101119785010000102003820038200382003820038
100242003715002621968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000644816101019785010000102003820038200382003820038
1002420037150026219687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006441116101019785010000102003820038200382003820038
1002420037150026219687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006441016101019785010000102003820038200382003820038
10024200371500262196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000064410168519785010000102003820038200382003820038
1002420037150026219687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006441016101019785010000102003820038200382003820038
100242003715002621968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000644101651019785010000102003820038200382003820038
10024200371500262196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000064481651019785010000102003820038200382003820038
1002420037150026219687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006441016101019785010000102003820038200382003820038
10024200371500262196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000064451651019785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  sqshl v0.8h, v1.8h, v0.8h
  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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150006119687251010010010000100100005002847680020018200372003718429718741101002001000820020016200372003711102011009910010010000100001117170160019802100001002003820038200382003820038
1020420037156006119687251010010010000100100005002847680120018200372003718429618741101002001000820020016200372003711102011009910010010000100001117180160019801100001002003820038200382003820038
102042003715049806119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371501206119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371503006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371501806119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715030886119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371502406119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

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)60696b6d6edispatch 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)9fa0a1a6a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371501010000026819687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000000006441316101019785010000102003820038200382003820038
10024200371501010000026819687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000000006441016101019785010000102003820038200382003820038
1002420037150101000002891968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000000644416111119785010000102003820038200382003820038
100242003715010100000268196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000000064481661119785010000102003820038200382003820038
1002420037150101000002681968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000000644816101019785010000102003820038200382003820038
10024200371501010000026819687251001010100001010000502847680120018020084200851844431878610164201016322203262008320084111002110910101000010000003006441116101019785010000102003820038200382003820038
10024200371501010000026819687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000000006441016101019785010000102003820038200382003820038
1002420037150101000003110196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000000064411168819785010000102003820038200382003820038
10024200371501010000026819687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000000006441016101019785010000102003820038200382003820038
10024200371501010000026819687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000000006441016101119785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  sqshl v0.8h, v8.8h, v9.8h
  sqshl v1.8h, v8.8h, v9.8h
  sqshl v2.8h, v8.8h, v9.8h
  sqshl v3.8h, v8.8h, v9.8h
  sqshl v4.8h, v8.8h, v9.8h
  sqshl v5.8h, v8.8h, v9.8h
  sqshl v6.8h, v8.8h, v9.8h
  sqshl v7.8h, v8.8h, v9.8h
  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)9fa0a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591500002004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511021611200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
8020420038150000039004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039

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)5f60696d6edispatch 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)9faccfd5d6daddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500183925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001005020121601213200352080000102003920039200392003920039
80024200381500039258001010800001080000506400000020019200382003899960310018800102080000201600002003820038118002110910108000010050207160911200350080000102003920039200392003920039
800242003815000392580010108000010800005064000000200192003820038999603100188001020800002016000020038200381180021109101080000100502091601010200350080000102003920039200392003920039
8002420038150036392580010108000010800005064000000200192003820038999603100188001020800002016000020038200381180021109101080000100502091601111200350080000102003920039200392003920039
80024200381500213925800101080000108000050640000112001920038200389996031001880010208000020160000200382003811800211091010800001005020121601310200350080000102003920039200392003920039
80024200381500393925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001005020111601010200350080000102003920039200392003920039
8002420038150003925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001005020101601010200350080000102003920039200392003920039
8002420038150033392580010108000010800005064000000200192003820038999603100188001020800002016000020038200381180021109101080000100502061601111200350080000102003920039200392003920039
8002420038150021392580010108000010800005064000000200192003820038999603100188001020800002016000020038200381180021109101080000100502091601010200350080000102003920039200392003920039
80024200381500633925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001005020111601010200350080000102003920039200392003920039