[X64] [xtqqczze] Reduce IL size for `BitConverter.GetBytes`

[MihuBot]

Build completed in 1 hour 17 minutes.
dotnet/runtime#91639

CoreLib diffs

Found 2 files with textual diffs.

Summary of Code Size diffs:
(Lower is better)

Total bytes of base: 6605438
Total bytes of diff: 6605377
Total bytes of delta: -61 (-0.00 % of base)
Total relative delta: -1.50
    diff is an improvement.
    relative diff is an improvement.


Top file improvements (bytes):
         -61 : System.Private.CoreLib.dasm (-0.00 % of base)

1 total files with Code Size differences (1 improved, 0 regressed), 0 unchanged.

Top method improvements (bytes):
         -26 (-56.52 % of base) : System.Private.CoreLib.dasm - System.BitConverter:GetBytes(float):ubyte[] (FullOpts)
         -23 (-52.27 % of base) : System.Private.CoreLib.dasm - System.BitConverter:GetBytes(double):ubyte[] (FullOpts)
         -12 (-41.38 % of base) : System.Private.CoreLib.dasm - System.BitConverter:GetBytes(System.Half):ubyte[] (FullOpts)

Top method improvements (percentages):
         -26 (-56.52 % of base) : System.Private.CoreLib.dasm - System.BitConverter:GetBytes(float):ubyte[] (FullOpts)
         -23 (-52.27 % of base) : System.Private.CoreLib.dasm - System.BitConverter:GetBytes(double):ubyte[] (FullOpts)
         -12 (-41.38 % of base) : System.Private.CoreLib.dasm - System.BitConverter:GetBytes(System.Half):ubyte[] (FullOpts)

3 total methods with Code Size differences (3 improved, 0 regressed), 52946 unchanged.

--------------------------------------------------------------------------------

Frameworks diffs

Diffs

Found 261 files with textual diffs.

Summary of Code Size diffs:
(Lower is better)

Total bytes of base: 37857688
Total bytes of diff: 37857695
Total bytes of delta: 7 (0.00 % of base)
Total relative delta: -0.62
    diff is a regression.
    relative diff is an improvement.


Top file regressions (bytes):
         124 : Microsoft.VisualBasic.Core.dasm (0.02 % of base)
          28 : ILCompiler.Reflection.ReadyToRun.dasm (0.01 % of base)

Top file improvements (bytes):
         -84 : System.Data.Common.dasm (-0.01 % of base)
         -61 : System.Private.CoreLib.dasm (-0.00 % of base)

4 total files with Code Size differences (2 improved, 2 regressed), 252 unchanged.

Top method regressions (bytes):
          71 (38.59 % of base) : Microsoft.VisualBasic.Core.dasm - Microsoft.VisualBasic.VBMath:Rnd(float):float (FullOpts)
          54 (45.76 % of base) : Microsoft.VisualBasic.Core.dasm - Microsoft.VisualBasic.VBMath:Randomize() (FullOpts)
          18 (1.58 % of base) : ILCompiler.Reflection.ReadyToRun.dasm - ILCompiler.Reflection.ReadyToRun.x86.GcInfo:GetTransitionsNoEbp(ubyte[],byref):this (FullOpts)
          10 (8.77 % of base) : ILCompiler.Reflection.ReadyToRun.dasm - ILCompiler.Reflection.ReadyToRun.x86.CallPattern:DecodeCallPattern(uint,byref,byref,byref,byref) (FullOpts)

Top method improvements (bytes):
         -84 (-5.99 % of base) : System.Data.Common.dasm - System.Data.Common.ObjectStorage:Set(int,System.Object):this (FullOpts)
         -26 (-56.52 % of base) : System.Private.CoreLib.dasm - System.BitConverter:GetBytes(float):ubyte[] (FullOpts)
         -23 (-52.27 % of base) : System.Private.CoreLib.dasm - System.BitConverter:GetBytes(double):ubyte[] (FullOpts)
         -12 (-41.38 % of base) : System.Private.CoreLib.dasm - System.BitConverter:GetBytes(System.Half):ubyte[] (FullOpts)
          -1 (-0.56 % of base) : Microsoft.VisualBasic.Core.dasm - Microsoft.VisualBasic.VBMath:Randomize(double) (FullOpts)

Top method regressions (percentages):
          54 (45.76 % of base) : Microsoft.VisualBasic.Core.dasm - Microsoft.VisualBasic.VBMath:Randomize() (FullOpts)
          71 (38.59 % of base) : Microsoft.VisualBasic.Core.dasm - Microsoft.VisualBasic.VBMath:Rnd(float):float (FullOpts)
          10 (8.77 % of base) : ILCompiler.Reflection.ReadyToRun.dasm - ILCompiler.Reflection.ReadyToRun.x86.CallPattern:DecodeCallPattern(uint,byref,byref,byref,byref) (FullOpts)
          18 (1.58 % of base) : ILCompiler.Reflection.ReadyToRun.dasm - ILCompiler.Reflection.ReadyToRun.x86.GcInfo:GetTransitionsNoEbp(ubyte[],byref):this (FullOpts)

Top method improvements (percentages):
         -26 (-56.52 % of base) : System.Private.CoreLib.dasm - System.BitConverter:GetBytes(float):ubyte[] (FullOpts)
         -23 (-52.27 % of base) : System.Private.CoreLib.dasm - System.BitConverter:GetBytes(double):ubyte[] (FullOpts)
         -12 (-41.38 % of base) : System.Private.CoreLib.dasm - System.BitConverter:GetBytes(System.Half):ubyte[] (FullOpts)
         -84 (-5.99 % of base) : System.Data.Common.dasm - System.Data.Common.ObjectStorage:Set(int,System.Object):this (FullOpts)
          -1 (-0.56 % of base) : Microsoft.VisualBasic.Core.dasm - Microsoft.VisualBasic.VBMath:Randomize(double) (FullOpts)

9 total methods with Code Size differences (5 improved, 4 regressed), 232293 unchanged.

--------------------------------------------------------------------------------

Artifacts:

• build-artifacts-main.zip (646 MB)
• build-clr-checked-main.zip (71 MB)
• build-artifacts-pr.zip (646 MB)
• build-clr-checked-pr.zip (71 MB)
• jit-diffs-corelib.zip (45 MB)
• diff-corelib.txt (1 KB)
• diff-frameworks.txt (3 KB)
• jit-diffs-frameworks.zip (246 MB)
• build-logs.txt (1 MB)

[MihuBot]

Top method improvements

-26 (-56.52 % of base) - System.BitConverter:GetBytes(float):ubyte[]

 ; Assembly listing for method System.BitConverter:GetBytes(float):ubyte[] (FullOpts)
 ; Emitting BLENDED_CODE for X64 with AVX - Unix
 ; FullOpts code
 ; optimized code
 ; rsp based frame
-; partially interruptible
+; fully interruptible
 ; No PGO data
 ; Final local variable assignments
 ;
-;  V00 arg0         [V00,T01] (  3,  3   )   float  ->  [rsp+0x04]  single-def
-;  V01 loc0         [V01,T00] (  3,  3   )     ref  ->  rax         class-hnd exact single-def <ubyte[]>
-;# V02 OutArgs      [V02    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
+;  V00 arg0         [V00,T00] (  3,  3   )   float  ->  mm0         single-def
+;# V01 OutArgs      [V01    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
 ;
-; Lcl frame size = 8
+; Lcl frame size = 0
 
 G_M32905_IG01:
-       push     rax
        vzeroupper 
-       vmovss   dword ptr [rsp+0x04], xmm0
-						;; size=10 bbWeight=1 PerfScore 3.00
+						;; size=3 bbWeight=1 PerfScore 1.00
 G_M32905_IG02:
-       mov      rdi, 0xD1FFAB1E      ; ubyte[]
-       mov      esi, 4
-       call     CORINFO_HELP_NEWARR_1_VC
-       vmovss   xmm0, dword ptr [rsp+0x04]
-       vmovss   dword ptr [rax+0x10], xmm0
-						;; size=31 bbWeight=1 PerfScore 6.50
+       vmovd    edi, xmm0
+       mov      rax, 0xD1FFAB1E      ; code for System.BitConverter:GetBytes(int):ubyte[]
+						;; size=14 bbWeight=1 PerfScore 2.25
 G_M32905_IG03:
-       add      rsp, 8
-       ret      
-						;; size=5 bbWeight=1 PerfScore 1.25
+       tail.jmp [rax]System.BitConverter:GetBytes(int):ubyte[]
+						;; size=3 bbWeight=1 PerfScore 2.00
 
-; Total bytes of code 46, prolog size 4, PerfScore 15.35, instruction count 10, allocated bytes for code 46 (MethodHash=41997f76) for method System.BitConverter:GetBytes(float):ubyte[] (FullOpts)
+; Total bytes of code 20, prolog size 3, PerfScore 7.25, instruction count 4, allocated bytes for code 20 (MethodHash=41997f76) for method System.BitConverter:GetBytes(float):ubyte[] (FullOpts)

-23 (-52.27 % of base) - System.BitConverter:GetBytes(double):ubyte[]

 ; Assembly listing for method System.BitConverter:GetBytes(double):ubyte[] (FullOpts)
 ; Emitting BLENDED_CODE for X64 with AVX - Unix
 ; FullOpts code
 ; optimized code
 ; rsp based frame
-; partially interruptible
+; fully interruptible
 ; No PGO data
 ; Final local variable assignments
 ;
-;  V00 arg0         [V00,T01] (  3,  3   )  double  ->  [rsp+0x00]  single-def
-;  V01 loc0         [V01,T00] (  3,  3   )     ref  ->  rax         class-hnd exact single-def <ubyte[]>
-;# V02 OutArgs      [V02    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
+;  V00 arg0         [V00,T00] (  3,  3   )  double  ->  mm0         single-def
+;# V01 OutArgs      [V01    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
 ;
-; Lcl frame size = 8
+; Lcl frame size = 0
 
 G_M20108_IG01:
-       push     rax
        vzeroupper 
-       vmovsd   qword ptr [rsp], xmm0
-						;; size=9 bbWeight=1 PerfScore 3.00
+						;; size=3 bbWeight=1 PerfScore 1.00
 G_M20108_IG02:
-       mov      rdi, 0xD1FFAB1E      ; ubyte[]
-       mov      esi, 8
-       call     CORINFO_HELP_NEWARR_1_VC
-       vmovsd   xmm0, qword ptr [rsp]
-       vmovsd   qword ptr [rax+0x10], xmm0
-						;; size=30 bbWeight=1 PerfScore 6.50
+       vmovd    rdi, xmm0
+       mov      rax, 0xD1FFAB1E      ; code for System.BitConverter:GetBytes(long):ubyte[]
+						;; size=15 bbWeight=1 PerfScore 2.25
 G_M20108_IG03:
-       add      rsp, 8
-       ret      
-						;; size=5 bbWeight=1 PerfScore 1.25
+       tail.jmp [rax]System.BitConverter:GetBytes(long):ubyte[]
+						;; size=3 bbWeight=1 PerfScore 2.00
 
-; Total bytes of code 44, prolog size 4, PerfScore 15.15, instruction count 10, allocated bytes for code 44 (MethodHash=02c0b173) for method System.BitConverter:GetBytes(double):ubyte[] (FullOpts)
+; Total bytes of code 21, prolog size 3, PerfScore 7.35, instruction count 4, allocated bytes for code 21 (MethodHash=02c0b173) for method System.BitConverter:GetBytes(double):ubyte[] (FullOpts)

-12 (-41.38 % of base) - System.BitConverter:GetBytes(System.Half):ubyte[]

 ; Assembly listing for method System.BitConverter:GetBytes(System.Half):ubyte[] (FullOpts)
 ; Emitting BLENDED_CODE for X64 with AVX - Unix
 ; FullOpts code
 ; optimized code
 ; rsp based frame
-; partially interruptible
+; fully interruptible
 ; No PGO data
+; 0 inlinees with PGO data; 1 single block inlinees; 0 inlinees without PGO data
 ; Final local variable assignments
 ;
 ;* V00 arg0         [V00    ] (  0,  0   )  struct ( 8) zero-ref    single-def <System.Half>
-;  V01 loc0         [V01,T01] (  3,  3   )     ref  ->  rax         class-hnd exact single-def <ubyte[]>
-;# V02 OutArgs      [V02    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
-;  V03 tmp1         [V03,T00] (  2,  2   )  ushort  ->  rbx         single-def "field V00._value (fldOffset=0x0)" P-INDEP
+;# V01 OutArgs      [V01    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
+;  V02 tmp1         [V02,T00] (  2,  2   )  ushort  ->  rdi         single-def "field V00._value (fldOffset=0x0)" P-INDEP
 ;
 ; Lcl frame size = 0
 
 G_M29041_IG01:
-       push     rbx
-       mov      ebx, edi
-						;; size=3 bbWeight=1 PerfScore 1.25
+						;; size=0 bbWeight=1 PerfScore 0.00
 G_M29041_IG02:
-       mov      rdi, 0xD1FFAB1E      ; ubyte[]
-       mov      esi, 2
-       call     CORINFO_HELP_NEWARR_1_VC
-       mov      word  ptr [rax+0x10], bx
-						;; size=24 bbWeight=1 PerfScore 2.50
+       movsx    rdi, di
+       mov      rax, 0xD1FFAB1E      ; code for System.BitConverter:GetBytes(short):ubyte[]
+						;; size=14 bbWeight=1 PerfScore 0.50
 G_M29041_IG03:
-       pop      rbx
-       ret      
-						;; size=2 bbWeight=1 PerfScore 1.50
+       tail.jmp [rax]System.BitConverter:GetBytes(short):ubyte[]
+						;; size=3 bbWeight=1 PerfScore 2.00
 
-; Total bytes of code 29, prolog size 1, PerfScore 8.15, instruction count 8, allocated bytes for code 29 (MethodHash=95fd8e8e) for method System.BitConverter:GetBytes(System.Half):ubyte[] (FullOpts)
+; Total bytes of code 17, prolog size 0, PerfScore 4.20, instruction count 3, allocated bytes for code 17 (MethodHash=95fd8e8e) for method System.BitConverter:GetBytes(System.Half):ubyte[] (FullOpts)

[MihuBot]

@MihaZupan