Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHL (scalar, B)

Test 1: uops

Code:

  sqshl b0, b0, b1
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150821687251000100010002646802018203720371572319131000100020002037203711100110001073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110008073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110001073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572618951000100020002037203711100110000073216221787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100017073216221787100020382038203820382038
10042037159611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshl b0, b0, b1
  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)031e3a3f4e51inst 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
10204200371500012619687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150006619687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000100071011611197910100001002003820038200382003820038
1020420037150006119687251010010010036100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011631198230100001002003820038200382003820038
1020420037150008219687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500014919687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500010519687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500041019687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03191e3f4e51inst 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)9fa0a1a6a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500021419687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219845010000102003820038200382003820038
10024200371500014519687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500014519687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000001020866402162219785010000102003820038200382003820038
100242003715000112919687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000001066402162219785010000102003820038200382003820038
10024200371500012419687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000001036402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500012419687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000001006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  sqshl b0, b1, b0
  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)030b181e1f3a3f4e51inst 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)9fa1a7a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000005361968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000075721622197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
102042003715000019201471968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071021622197910100001002003820038200872023120038
1020420037150000001491968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
1020420037149000001701968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
1020420037150000003131968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071021622197910100001002003820038200712003820038
1020420037150000001681968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
1020420037150000001241968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000100071021622197912100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)60696b6d6edispatch 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
100242003715000000015119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000001006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000606119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000012419687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000013619687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000009519687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715600000019319687251001010100001010000502847680020018320037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000010519687251001010100001010000502847680020018020037200371844431876710010201000020200002003720073111002110910101000010000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  sqshl b0, b8, b9
  sqshl b1, b8, b9
  sqshl b2, b8, b9
  sqshl b3, b8, b9
  sqshl b4, b8, b9
  sqshl b5, b8, b9
  sqshl b6, b8, b9
  sqshl b7, b8, b9
  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)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)9fa0a1a6a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420048150000000292580108100800081008002050064013202001920038200389977699898012020080032200160064200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200160064200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
8020420038150000000292580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511011611200350800001002003920039200392003920039
80204200381500000001352580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

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)9fa6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000050201161120035080000102003920039200392003920039
8002420038150000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000050201161120035080000102003920039200392003920039
80024200381500000029425800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000050201161120035080000102003920039200392003920039
8002420038150000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000050201161120035080000102003920039200392003920039
8002420038150000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000050201161120035080000102003920039200392003920039
8002420038150000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000050204161120035080000102003920039200392003920039
80024200381500000014825800101080000108000050640000120019200382003899963100188001020800002016019420038200381180021109101080000100000050201161120035080000102003920039200392003920039
8002420038150000008125800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100020050201161120035080000102003920039200392003920039
8002420038150000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000102000050201161120035080000102003920039200392003920039
8002420038150000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000050201161120035080000102003920039202412003920039