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, 4S)

Test 1: uops

Code:

  sqshl v0.4s, v0.4s, v1.4s
  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
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111785100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000373116221785100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000075116221787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116211787100020382038203820382038
100420371666116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382085
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshl v0.4s, v0.4s, v1.4s
  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)0308090b18191e1f3a3f4e51inst 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
10204200371500000000027819687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000000041719687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000100071011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000000066719687251010010010000100100005002847680020018200372008518422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000000098519687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000000018919687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000100071011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715000000000613196764410127130100121081015258428489630200542008420085184268187631026520610164202203282008420085211020110099100100100001000200019652735125111982719100001002008620086200852013220087

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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640316221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010090640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820183200382003820038
100242003715000611968725100101010000101015250284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150009841968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715003611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010100640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  sqshl v0.4s, v1.4s, v0.4s
  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)03070818191e1f3a3f4e51inst 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)9fa0a8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420084150000000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710216221979125100001002003820038200382003820038
10204200371500000000100319687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000171021622197910100001002003820038200382003820038
102042003715000000006119687441011710010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
102042003715000000006119687251012512510000125100006262847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
102042003715010000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021623197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021623197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst 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)9fa0a1a6a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000000012419687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000000012419687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200842003718444318767100102010000202000020037200371110021109101010000100000606402162219785010000102003820038200382003820038
1002420037150000000008419687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000000025119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  sqshl v0.4s, v8.4s, v9.4s
  sqshl v1.4s, v8.4s, v9.4s
  sqshl v2.4s, v8.4s, v9.4s
  sqshl v3.4s, v8.4s, v9.4s
  sqshl v4.4s, v8.4s, v9.4s
  sqshl v5.4s, v8.4s, v9.4s
  sqshl v6.4s, v8.4s, v9.4s
  sqshl v7.4s, v8.4s, v9.4s
  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)030809191e3f51inst 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
802042005815000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102161120035800001002003920039200392003920039
8020420038150000046025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000651102161220035800001002003920039200392003920039
802042003815000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120112800001002003920039200392003920039
802042003815000004025801001008000010080000500640000120019200382011199823999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815000008225801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102161120035800001002003920039200392003920039
802042003814900004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b191e3a3f51inst 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)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)9fa8accfd5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047150000060258001010800001080000506400000120019200382003899963100188001020800002016000020087200381180021109101080000100050206165352003580000102003920039200392003920039
8002420038150000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050203164352003580000102003920039200392003920039
8002420038150000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050205162352011180000102003920039200392003920039
8002420038150000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050203164532003580000102003920039200392003920039
8002420038150000039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050204164452003580000102003920039200392003920039
8002420038150000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050203162552003580000102003920039200392003920039
8002420038150000039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050206164462003580000102003920039200392003920039
8002420038150000039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100650206162362003580000102003920039200392003920039
8002420038150000039498001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050205164362003580000102003920039200392003920039
8002420038150000039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050204162352003580000102003920039200392003920039