JIT does not always fold inlined constants #62604
Description
It appears that JIT (x64) sometimes misses opportunities for folding inlined(?) constants.
The following code demonstrates the issue. Depending on the order of the addends in C#, constants are more or less folded.
I did assume that order in C# would not impact JITs ability to fold them.
There are two pairs of methods, CalculateMaxSize[No]ExtraAdd and CalculateMaxSize[No]ExtraInc.
The *No* variants look like what I had expected for either implementation.
using System.Runtime.CompilerServices;
internal readonly struct SubId {
public static int MaxSize => 16;
}
internal readonly struct MyStruct
{
public static ReadOnlySpan<byte> EoL => new []{(byte)'\r', (byte)'\n'};
internal readonly byte[] _subject;
public MyStruct(byte[] subject){
_subject = subject;
}
/*
mov rax, gword ptr [rdi]
mov eax, dword ptr [rax+8]
add eax, 18
*/
[MethodImpl(MethodImplOptions.NoInlining)]
public int CalculateMaxSizeNoExtraAdd()
{
return SubId.MaxSize + EoL.Length + _subject.Length;
}
/*
mov rax, gword ptr [rdi]
mov eax, dword ptr [rax+8]
add eax, 16
add eax, 2
*/
[MethodImpl(MethodImplOptions.NoInlining)]
public int CalculateMaxSizeExtraAdd()
{
// This will emit two add instructions even when making SubId.MaxSize a const field
return _subject.Length + SubId.MaxSize + EoL.Length;
}
/*
mov rax, gword ptr [rdi]
mov eax, dword ptr [rax+8]
add eax, 17
*/
[MethodImpl(MethodImplOptions.NoInlining)]
public int CalculateMaxSizeNoExtraInc()
{
return _subject.Length + SubId.MaxSize + 1;
}
/*
mov rax, gword ptr [rdi]
mov eax, dword ptr [rax+8]
inc eax // This does not repro on .NET 7.0, it now emits a single add eax, 17 ❤
add eax, 16
*/
[MethodImpl(MethodImplOptions.NoInlining)]
public int CalculateMaxSizeExtraInc()
{
return _subject.Length + 1 + SubId.MaxSize;
}
}Sharplap and JIT dump running 1d4b5f6
; Assembly listing for method foo.MyStruct:CalculateMaxSizeNoExtraAdd():int:this
; Emitting BLENDED_CODE for X64 CPU with AVX - Unix
; Tier-1 compilation
; optimized code
; rsp based frame
; partially interruptible
; No PGO data
; 1 inlinees with PGO data; 5 single block inlinees; 0 inlinees without PGO data
; Final local variable assignments
;
; V00 this [V00,T00] ( 3, 3 ) byref -> rdi this single-def
;* V01 loc0 [V01 ] ( 0, 0 ) struct (16) zero-ref ld-addr-op
;# V02 OutArgs [V02 ] ( 1, 1 ) lclBlk ( 0) [rsp+00H] "OutgoingArgSpace"
;* V03 tmp1 [V03 ] ( 0, 0 ) int -> zero-ref "impAppendStmt"
;* V04 tmp2 [V04 ] ( 0, 0 ) struct (16) zero-ref "NewObj constructor temp"
;* V05 tmp3 [V05 ] ( 0, 0 ) struct ( 8) zero-ref "NewObj constructor temp"
;* V06 tmp4 [V06 ] ( 0, 0 ) byref -> zero-ref single-def V01._pointer(offs=0x00) P-INDEP "field V01._pointer (fldOffset=0x0)"
;* V07 tmp5 [V07 ] ( 0, 0 ) int -> zero-ref single-def V01._length(offs=0x08) P-INDEP "field V01._length (fldOffset=0x8)"
;* V08 tmp6 [V08 ] ( 0, 0 ) byref -> zero-ref V04._pointer(offs=0x00) P-INDEP "field V04._pointer (fldOffset=0x0)"
;* V09 tmp7 [V09 ] ( 0, 0 ) int -> zero-ref V04._length(offs=0x08) P-INDEP "field V04._length (fldOffset=0x8)"
;* V10 tmp8 [V10 ] ( 0, 0 ) byref -> zero-ref single-def V05._value(offs=0x00) P-INDEP "field V05._value (fldOffset=0x0)"
;
; Lcl frame size = 0
G_M57648_IG01:
;; bbWeight=1 PerfScore 0.00
G_M57648_IG02:
mov rax, gword ptr [rdi]
mov eax, dword ptr [rax+8]
add eax, 18
;; bbWeight=1 PerfScore 4.25
G_M57648_IG03:
ret
;; bbWeight=1 PerfScore 1.00
; Total bytes of code 10, prolog size 0, PerfScore 6.25, instruction count 4, allocated bytes for code 10 (MethodHash=f2321ecf) for method foo.MyStruct:CalculateMaxSizeNoExtraAdd():int:this
; ============================================================
; Assembly listing for method foo.MyStruct:CalculateMaxSizeExtraAdd():int:this
; Emitting BLENDED_CODE for X64 CPU with AVX - Unix
; Tier-1 compilation
; optimized code
; rsp based frame
; partially interruptible
; No PGO data
; 1 inlinees with PGO data; 5 single block inlinees; 0 inlinees without PGO data
; Final local variable assignments
;
; V00 this [V00,T00] ( 3, 3 ) byref -> rdi this single-def
;* V01 loc0 [V01 ] ( 0, 0 ) struct (16) zero-ref ld-addr-op
;# V02 OutArgs [V02 ] ( 1, 1 ) lclBlk ( 0) [rsp+00H] "OutgoingArgSpace"
; V03 tmp1 [V03,T01] ( 2, 4 ) int -> rax "impAppendStmt"
; V04 tmp2 [V04,T02] ( 2, 4 ) int -> rax "impAppendStmt"
;* V05 tmp3 [V05 ] ( 0, 0 ) struct (16) zero-ref "NewObj constructor temp"
;* V06 tmp4 [V06 ] ( 0, 0 ) struct ( 8) zero-ref "NewObj constructor temp"
;* V07 tmp5 [V07 ] ( 0, 0 ) byref -> zero-ref single-def V01._pointer(offs=0x00) P-INDEP "field V01._pointer (fldOffset=0x0)"
;* V08 tmp6 [V08 ] ( 0, 0 ) int -> zero-ref single-def V01._length(offs=0x08) P-INDEP "field V01._length (fldOffset=0x8)"
;* V09 tmp7 [V09 ] ( 0, 0 ) byref -> zero-ref V05._pointer(offs=0x00) P-INDEP "field V05._pointer (fldOffset=0x0)"
;* V10 tmp8 [V10 ] ( 0, 0 ) int -> zero-ref V05._length(offs=0x08) P-INDEP "field V05._length (fldOffset=0x8)"
;* V11 tmp9 [V11 ] ( 0, 0 ) byref -> zero-ref single-def V06._value(offs=0x00) P-INDEP "field V06._value (fldOffset=0x0)"
;
; Lcl frame size = 0
G_M14833_IG01:
;; bbWeight=1 PerfScore 0.00
G_M14833_IG02:
mov rax, gword ptr [rdi]
mov eax, dword ptr [rax+8]
add eax, 16
add eax, 2
;; bbWeight=1 PerfScore 4.50
G_M14833_IG03:
ret
;; bbWeight=1 PerfScore 1.00
; Total bytes of code 13, prolog size 0, PerfScore 6.80, instruction count 5, allocated bytes for code 13 (MethodHash=cc45c60e) for method foo.MyStruct:CalculateMaxSizeExtraAdd():int:this
; ============================================================
; Assembly listing for method foo.MyStruct:CalculateMaxSizeNoExtraInc():int:this
; Emitting BLENDED_CODE for X64 CPU with AVX - Unix
; Tier-1 compilation
; optimized code
; rsp based frame
; partially interruptible
; No PGO data
; 0 inlinees with PGO data; 1 single block inlinees; 0 inlinees without PGO data
; Final local variable assignments
;
; V00 this [V00,T00] ( 3, 3 ) byref -> rdi this single-def
;# V01 OutArgs [V01 ] ( 1, 1 ) lclBlk ( 0) [rsp+00H] "OutgoingArgSpace"
; V02 tmp1 [V02,T01] ( 2, 4 ) int -> rax "impAppendStmt"
;
; Lcl frame size = 0
G_M11669_IG01:
;; bbWeight=1 PerfScore 0.00
G_M11669_IG02:
mov rax, gword ptr [rdi]
mov eax, dword ptr [rax+8]
add eax, 17
;; bbWeight=1 PerfScore 4.25
G_M11669_IG03:
ret
;; bbWeight=1 PerfScore 1.00
; Total bytes of code 10, prolog size 0, PerfScore 6.25, instruction count 4, allocated bytes for code 10 (MethodHash=d8a9d26a) for method foo.MyStruct:CalculateMaxSizeNoExtraInc():int:this
; ============================================================
; Assembly listing for method foo.MyStruct:CalculateMaxSizeExtraInc():int:this
; Emitting BLENDED_CODE for X64 CPU with AVX - Unix
; Tier-1 compilation
; optimized code
; rsp based frame
; partially interruptible
; No PGO data
; 0 inlinees with PGO data; 1 single block inlinees; 0 inlinees without PGO data
; Final local variable assignments
;
; V00 this [V00,T00] ( 3, 3 ) byref -> rdi this single-def
;# V01 OutArgs [V01 ] ( 1, 1 ) lclBlk ( 0) [rsp+00H] "OutgoingArgSpace"
; V02 tmp1 [V02,T01] ( 2, 4 ) int -> rax "impAppendStmt"
;
; Lcl frame size = 0
G_M56724_IG01:
;; bbWeight=1 PerfScore 0.00
G_M56724_IG02:
mov rax, gword ptr [rdi]
mov eax, dword ptr [rax+8]
inc eax
add eax, 16
;; bbWeight=1 PerfScore 4.50
G_M56724_IG03:
ret
;; bbWeight=1 PerfScore 1.00
; Total bytes of code 12, prolog size 0, PerfScore 6.70, instruction count 5, allocated bytes for code 12 (MethodHash=17e2226b) for method foo.MyStruct:CalculateMaxSizeExtraInc():int:this
; ============================================================ category:implementation
theme:inlining
skill-level:intermediate
cost:medium
impact:medium