Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSHL (immediate, vector, 16B)

Test 1: uops

Code:

  uqshl v0.16b, v0.16b, #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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371606116862510001000100026452120182037207315713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371606116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203716126116862510001000100026452120182037203715713189510001000100020372037111001100000073137111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  uqshl v0.16b, v0.16b, #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)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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003714900000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000000061196862510100100100001041000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611198550100001002003820038200382003820038
10204200371500002370061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500002130061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037211020110099100100100001000000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)9facc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715045061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640516541978610000102003820038200382003820038
100242003714900251196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640516541978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640516541978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640516541978610000102003820038200382003820038
100242003715045061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640416541978610000102017820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640516451978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640516551978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640516451978610000102003820038200382003820038
10024200371509061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640516551978610000102003820038200382003820074
100242003715000726196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640516551978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  uqshl v0.16b, v8.16b, #3
  uqshl v1.16b, v8.16b, #3
  uqshl v2.16b, v8.16b, #3
  uqshl v3.16b, v8.16b, #3
  uqshl v4.16b, v8.16b, #3
  uqshl v5.16b, v8.16b, #3
  uqshl v6.16b, v8.16b, #3
  uqshl v7.16b, v8.16b, #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)031e3f51inst 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)9fc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006115002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010011151183162120035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010011151182161220035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200882003899776998980120200800322008003220038200381180201100991001008000010011151182162120035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010011151182162120035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010011151182162120035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010011151182162220035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010011151182163220035800001002003920039200392003920039
8020420038150212925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010011151182162120035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010011151182162320035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010011151182162220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a0b18191e1f3f51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000000006725800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050203164220035080000102003920039200392003920039
800242003815000000003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050204162420035080000102003920039200392003920039
8002420038150000003603925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050204162420035080000102003920039200392003920039
800242003815000000003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050202164420035080000102003920039200392003920039
800242003815000000003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050204164220035080000102003920039200392003920039
800242003815000000003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050204164420035080000102003920039200392003920039
800242003815000000003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050202162420035080000102003920039200392003920039
800242003815000000003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050204162420035080000102003920039200392003920039
80024200381500000038703925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050202164420035080000102003920039200392003920039
80024200381500000025803925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050204163420035080000102003920039200392003920039