Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHL (immediate, scalar, H)

Test 1: uops

Code:

  sqshl h0, h0, #3
  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)0308090b18191e1f3f4e51inst 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)a0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150000000611686251000100010002645210201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
10042037160000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
10042037150000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
100420371600000601051686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
10042037150000030611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
10042037150000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
10042037150000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
10042037150000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
10042037150000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
10042037150000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshl h0, h0, #3
  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)030b18191e3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000005361968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000001601968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010020071011611197910100001002003820038200382003820038
102042003715000001871968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0304080b18191e3a3f4e51inst 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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242008415000000326619686251001010100001010000502847521020018200372003718447318767100102010000201000020037200371110021109101010000100020644616111119786010000102017920085200382003820038
1002420037150000002121081968644100101010000101000050284878502005420037200371844331876710010201000020101682003720037111002110910101000010421120206441116111119786210000102022620281202772031020038
1002420037150111556602661962025100101010000101000050284752102023420037201791844911188041046920100002010000200372003711100211091010100001000006441116111119786010000102003820038200382003820038
1002420037150000000266196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006441316111119786010000102003820038200382003820038
100242003715000000026619686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100013644111691119786010000102003820038200382003820038
1002420037150000000266196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000036441116111119786010000102003820038200382003820038
1002420037150000000266196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000166441116111119786010000102003820038200382003820038
100242003715000000026619686251001010100001010000502847521020018200372003718443318767100102010000201000020037200372110021109101010000100010644916111219786010000102003820038200382003820038
1002420037150000000266196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006441116111219786010000102003820038200382003820038
100242003715000000026619686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000644616111119786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sqshl h0, h8, #3
  sqshl h1, h8, #3
  sqshl h2, h8, #3
  sqshl h3, h8, #3
  sqshl h4, h8, #3
  sqshl h5, h8, #3
  sqshl h6, h8, #3
  sqshl h7, h8, #3
  movi v8.16b, 9

(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)9fa0a1a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150000108824725801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511801602200350800001002003920039200392009020091
802042003815000002102925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511801600200350800001002003920039200392003920039
80204200381500000002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511801600200350800001002003920039200392003920039
80204200381500000007125801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511801600200350800001002003920039200392003920039
80204200381500000002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511801600200350800001002003920039200392003920039
80204200381510012602925801081008000810080020500640132120019200382003899866998980120200800322008003220099201472180201100991001008000010043100111511801600200350800001002003920039200392003920039
802042003815000002402925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511801600200350800001002003920039200392003920039
80204200381500000002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511801600200350800001002003920039200392003920039
802042003815000003602925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511801600200350800001002003920039200392003920039
802042003815000002402925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000111511801600200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)9fcficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500012752580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001050200516642003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001050200416432003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001050200416772003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001050200416342003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001050200416672003580000102003920039200392003920039
80024200381500129392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001050200716372003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001050200316762003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001050200616762003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001050200616442003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001050200416432003580000102003920039200392003920039