Apple M1 Microarchitecture Research by Dougall Johnson

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

SHL (vector, 2S)

Test 1: uops

Code:

  shl v0.2s, v0.2s, #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)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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150821686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037160611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150841686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  shl v0.2s, v0.2s, #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)031e3f4e51inst 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)9fa0a6cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150666119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715096119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
10204200371503846119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715096119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100027102162219791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030818191e1f3a3f4e51inst 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
10024200371500000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000100206706407166519786010000102003820038200382003820038
1002420037150000300611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006406166519786010000102003820038200382003820038
100242003715000048300611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006405165619786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006405166519786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006406166519786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006406166519786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752102001820037200371844331876710010201017820100002003720037111002110910101000010000000006405165619786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006406165619786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006405165519786010000102003820038200382003820038
10024200371500002100611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006405166519786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  shl v0.2s, v8.2s, #3
  shl v1.2s, v8.2s, #3
  shl v2.2s, v8.2s, #3
  shl v3.2s, v8.2s, #3
  shl v4.2s, v8.2s, #3
  shl v5.2s, v8.2s, #3
  shl v6.2s, v8.2s, #3
  shl v7.2s, v8.2s, #3
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)030b18191e1f3f51inst 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)9fa1a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060150000902925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151181160020035800001002003920039200392003920039
8020420038150000002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000311151180160020035800001002003920039200392003920039
8020420038150000902925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
80204200381500003069425801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150000002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150000002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038151001602925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150000006426801161008001610080128500640000120028200472004799716999380100200800002008000020047200471180201100991001008000010000011151202242220044800001002010120048200482004820109
8020420047151000007527801001008000010080000500640000120028200472004799716999380100200800002008000020047200471180201100991001008000010000011151202242220044800001002004820048200482004820048
8020420047150000007527801001008000010080000500640000120028200472004799716999380100200800002008000020047200471180201100991001008000010000011151202242220044800001002004820048200482004820048

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e1f3f51inst 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
8002420051150000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100005020116112003580000102003920039200392003920039
8002420038150090392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100005020116112003580000102003920039200392003920039
80024200381500088392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100005037116112003580000102003920039200392003920039
80024200381500120392580010108000010800005064000012001920038200879996810018800102080000208000020038200381180021109101080000100005020116212003580000102003920039200392003920039
800242003815000108392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000102005020116112003580000102003920039200392003920039
8002420038150000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100005020116112003580000102003920039200392003920039
8002420038150000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100005020116112003580000102003920039200392003920039
80024200381503153010142580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100005020116112003580000102003920039200392003920039
8002420038150000392580010108000010800005064000012001920038200389996310018800102080000208019520038200381180021109101080000100005020116212003580000102003920039200392003920039
8002420038150000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100005020116112003580000102003920039200392003920039