DrSocalkwe3n/luajit
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix pow() optimization inconsistencies.

Browse Source
This commit is contained in:
Mike Pall
2022-01-24 14:37:50 +01:00
parent c18acfe756
commit 9512d5c1ac
15 changed files with 114 additions and 205 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
src/vm_x86.dasc
View File

@@ -2138,8 +2138,8 @@ static void build_subroutines(BuildCtx *ctx)
| jmp ->fff_resfp
|.endmacro
|
|.macro math_extern2, func
| .ffunc_nnsse math_ .. func
|.macro math_extern2, name, func
| .ffunc_nnsse math_ .. name
|.if not X64
| movsd FPARG1, xmm0
| movsd FPARG3, xmm1
@@ -2149,6 +2149,9 @@ static void build_subroutines(BuildCtx *ctx)
| mov BASE, RB
| jmp ->fff_resfp
|.endmacro
|.macro math_extern2, func
| math_extern2 func, func
|.endmacro
|
| math_extern log10
| math_extern exp
@@ -2161,7 +2164,7 @@ static void build_subroutines(BuildCtx *ctx)
| math_extern sinh
| math_extern cosh
| math_extern tanh
| math_extern2 pow
| math_extern2 pow, lj_vm_pow
| math_extern2 atan2
| math_extern2 fmod
|
@@ -3038,41 +3041,6 @@ static void build_subroutines(BuildCtx *ctx)
| subsd xmm0, xmm1
| ret
|
|// Args in xmm0/eax. Ret in xmm0. xmm0-xmm1 and eax modified.
|->vm_powi_sse:
| cmp eax, 1; jle >6 // i<=1?
| // Now 1 < (unsigned)i <= 0x80000000.
|1: // Handle leading zeros.
| test eax, 1; jnz >2
| mulsd xmm0, xmm0
| shr eax, 1
| jmp <1
|2:
| shr eax, 1; jz >5
| movaps xmm1, xmm0
|3: // Handle trailing bits.
| mulsd xmm0, xmm0
| shr eax, 1; jz >4
| jnc <3
| mulsd xmm1, xmm0
| jmp <3
|4:
| mulsd xmm0, xmm1
|5:
| ret
|6:
| je <5 // x^1 ==> x
| jb >7 // x^0 ==> 1
| neg eax
| call <1
| sseconst_1 xmm1, RDa
| divsd xmm1, xmm0
| movaps xmm0, xmm1
| ret
|7:
| sseconst_1 xmm0, RDa
| ret
|
|//-----------------------------------------------------------------------
|//-- Miscellaneous functions --------------------------------------------
|//-----------------------------------------------------------------------
@@ -3954,7 +3922,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
| movsd FPARG1, xmm0
| movsd FPARG3, xmm1
|.endif
| call extern pow
| call extern lj_vm_pow
| movzx RA, PC_RA
| mov BASE, RB
|.if X64