6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-14 11:32:34 +00:00
Code Issues Projects Releases Wiki Activity

Remove outdated README-SSE.txt entries.

Browse Source 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@233292 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Benjamin Kramer 2015-03-26 17:12:16 +00:00
parent 8f820e9495
commit aa66f225d2
1 changed files with 0 additions and 78 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

78
lib/Target/X86/README-SSE.txt
View File

@ -93,36 +93,6 @@ The pattern isel got this one right.
//===---------------------------------------------------------------------===//
SSE should implement 'select_cc' using 'emulated conditional moves' that use
pcmp/pand/pandn/por to do a selection instead of a conditional branch:
double %X(double %Y, double %Z, double %A, double %B) {
%C = setlt double %A, %B
%z = fadd double %Z, 0.0 ;; select operand is not a load
%D = select bool %C, double %Y, double %z
ret double %D
}
We currently emit:
_X:
subl $12, %esp
xorpd %xmm0, %xmm0
addsd 24(%esp), %xmm0
movsd 32(%esp), %xmm1
movsd 16(%esp), %xmm2
ucomisd 40(%esp), %xmm1
jb LBB_X_2
LBB_X_1:
movsd %xmm0, %xmm2
LBB_X_2:
movsd %xmm2, (%esp)
fldl (%esp)
addl $12, %esp
ret
//===---------------------------------------------------------------------===//
Lower memcpy / memset to a series of SSE 128 bit move instructions when it's
feasible.
@ -787,25 +757,6 @@ cheaper to do fld1 than load from a constant pool for example, so
//===---------------------------------------------------------------------===//
The X86 backend should be able to if-convert SSE comparisons like "ucomisd" to
"cmpsd". For example, this code:
double d1(double x) { return x == x ? x : x + x; }
Compiles into:
_d1:
ucomisd %xmm0, %xmm0
jnp LBB1_2
addsd %xmm0, %xmm0
ret
LBB1_2:
ret
Also, the 'ret's should be shared. This is PR6032.
//===---------------------------------------------------------------------===//
These should compile into the same code (PR6214): Perhaps instcombine should
canonicalize the former into the later?
@ -858,35 +809,6 @@ doing a shuffle from v[1] to v[0] then a float store.
//===---------------------------------------------------------------------===//
On SSE4 machines, we compile this code:
define <2 x float> @test2(<2 x float> %Q, <2 x float> %R,
<2 x float> *%P) nounwind {
%Z = fadd <2 x float> %Q, %R
store <2 x float> %Z, <2 x float> *%P
ret <2 x float> %Z
}
into:
_test2: ## @test2
## BB#0:
insertps $0, %xmm2, %xmm2
insertps $16, %xmm3, %xmm2
insertps $0, %xmm0, %xmm3
insertps $16, %xmm1, %xmm3
addps %xmm2, %xmm3
movq %xmm3, (%rdi)
movaps %xmm3, %xmm0
pshufd $1, %xmm3, %xmm1
## kill: XMM1<def> XMM1<kill>
ret
The insertps's of $0 are pointless complex copies.
//===---------------------------------------------------------------------===//
[UNSAFE FP]
void foo(double, double, double);