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, B)

Test 1: uops

Code:

  sqshl b0, b0, #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)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)a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
1004203715516116862510001000100026452120182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100003073216221786100020382038203820382038
1004203715061168625100010001000264521201820372037157131895100010001000203720371110011000120473216221786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100010073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshl b0, b0, #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)030b1e1f3f4e51inst 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)9fa0a1a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000057919686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000441196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001004046000071011611197910100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715000016819686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715000010319686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011711197910100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715000016619686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b18191e1f3a3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000001271968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216321978610000102003820038200382003820038
10024200371500000001031968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216321978610000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216321978610000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640416221978610000102003820038200382003820038
1002420037150000378007701968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216321978610000102003820038200382003820038
100242003715000000063819686251001010100001010000502847521120018200372003718443318787100102010000201000020037200371110021109101010000102700640216321978610000102003820038200382003820038
1002420037150000000841968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216321978610000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216321978610000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500000007261968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sqshl b0, b8, #3
  sqshl b1, b8, #3
  sqshl b2, b8, #3
  sqshl b3, b8, #3
  sqshl b4, b8, #3
  sqshl b5, b8, #3
  sqshl b6, b8, #3
  sqshl b7, b8, #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)030918191e1f3f4e51inst 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)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)9fa1a8a9acc2c5branch mispredict (cb)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571500000011702580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118116020035800001002003920039200392003920039
80204200381500003059902580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
8020420038150000002902580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
80204200381500000029025801081008000810080020500640132020019200382003899770699898012020080032200800322003820038118020110099100100800001000500301115118016020035800001002003920039200392003920039
8020420038150000002902580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
80204200381550000064502580108100800081008002050064013202001920038200389977069989801202008003220080032200872003811802011009910010080000100000001115118016020035800001002003920039200392003920039
8020420038150000002902580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
8020420038150000002902580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
8020420038150000002902580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
8020420038150001002902580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080b18191e1f3a3f51inst 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)6061696d6edispatch 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)9fa0a1a6a8a9acc2cfd0d2d5d6d9ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150000001800392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000050240017162121520035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001000000005020001616261320035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001000000005020001616261620035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001000000005020001616451520035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000000502000716261620035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001000000005020001616216620035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001000000305020001616251620035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100001000503700616212520035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001000000005020001616251720035280000102003920039200392003920039
800242003815000000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000050200016162161620035080000102003920039200392003920039