Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSHL (scalar, H)

Test 1: uops

Code:

  uqshl h0, h0, h1
  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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715084168725100010001000264680020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
10042037150105168725100010001000264680020182037203715723189510001000200020372037111001100000373216221787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100001073216221787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
1004203715093168725100010001000264680120182037203715723189510001000200020372037111001100000373216221787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  uqshl h0, h0, h1
  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)9fa1a7a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371610006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071031622197910100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000900071021622197910100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000011171811611198010100001002003820038200382003820038
1020420037150000223119687251010010010000100100005002847680020018200372003718429618741101002001000820020016200372003711102011009910010010000100000011171711611198010100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100001000071021622197910100001002003820038200382003820038

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)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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000018919687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000000006402162219849010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000000006402162119785010000102003820038200382003820038
1002420037150000063018919687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100001100006403162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000100006402162219785010000102003820038200382003820038
10024200371500000008419687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000000006403162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000000006403162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uqshl h0, h1, h0
  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)03081e1f3f4e51inst 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)9fa0acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500003461968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200841110201100991001001000010000007101161119791100001002003820038200382003820038
1020420084150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000017101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371490001411968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03181e3f4e51inst 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)9faccdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000642216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000642216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000642216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000642216221978510000102003820038200382003820038
100242003715001561196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001060642216221978510000102003820038200382003820038
10024200371500084196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000642216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000642216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000642216221978510000102003820038200382003820038
100242003715000677196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100221091010100001000642216221978510000102003820038200382003820038
100242003715004261196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000642216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uqshl h0, h8, h9
  uqshl h1, h8, h9
  uqshl h2, h8, h9
  uqshl h3, h8, h9
  uqshl h4, h8, h9
  uqshl h5, h8, h9
  uqshl h6, h8, h9
  uqshl h7, h8, h9
  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)030b191e3f51inst 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)9fa8c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005615000029258010810080008100800205006401322001920038200389977699898012020080032200160064200382003811802011009910010080000100011151180160020035800001002003920039200392003920039
802042003815000050258010810080008100800205006401322001920038200389977699898012020080032200160064200382003811802011009910010080000100011151180160020035800001002003920039200392003920039
802042003815000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400002001920038200389973399968010020080000200160188200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
8020420038150000610258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051351161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080a0b18191e1f3a3f51inst 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)9fa0a1a6a8acc2c5cfd0d2icache miss (d3)d5d6d9daddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915010100000246258001010800001080000506400000120019200382003899963100188001020801322016000020038200381180021109101080000100000000502400017160016162003500080000102003920039200392003920039
800242003815010100000246258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100000000502400013160014152003500080000102003920039200392003920039
800242003815010100000246258001010800001080000506400000120019200382003899963100188001020800002016058420038200381180021109101080000100000000502400019160017162003520080000102003920039200392003920039
800242003815010100000246258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100000000502400016160016162003500080000102003920039200392003920039
800242003815010100000246258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100000000502400017160016152003500080000102003920039200392003920039
800242003815010100000246258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100000000502400011160016112003500080000102003920039200392003920039
800242003815010100000246258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100000000502400013160016132003500080000102003920039200392003920039
800242003815010100000246258001010800001080000506400000120019200382003899963100188001020800002016038620038200381180021109101080000100000000502400017160017162003500080000102003920039200392003920039
800242003815010100000246258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100000000502400017160013162003500080000102003920039200392003920039
800242003815010100060246258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100000000502400017160017162003500080000102003920039200392003920039