[llvm-commits] CVS: llvm/lib/Target/X86/README.txt

[Chris Lattner]

Changes in directory llvm/lib/Target/X86:

README.txt updated: 1.146 -> 1.147
---
Log message:

Update note, with the SROA change, we now produce:

_pairtest:
        movl 8(%esp), %eax
        movl 4(%esp), %ecx
        movd %eax, %xmm0
        movd %ecx, %xmm1
        addss %xmm0, %xmm1
        movl 12(%esp), %eax
        movss %xmm1, (%eax)
        ret

instead of:

_pairtest:
        subl $12, %esp
        movl 20(%esp), %eax
        movl %eax, 4(%esp)
        movl 16(%esp), %eax
        movl %eax, (%esp)
        movss (%esp), %xmm0
        addss 4(%esp), %xmm0
        movl 24(%esp), %eax
        movss %xmm0, (%eax)
        addl $12, %esp
        ret



---
Diffs of the changes:  (+11 -10)

 README.txt |   21 +++++++++++----------
 1 files changed, 11 insertions(+), 10 deletions(-)


Index: llvm/lib/Target/X86/README.txt
diff -u llvm/lib/Target/X86/README.txt:1.146 llvm/lib/Target/X86/README.txt:1.147
--- llvm/lib/Target/X86/README.txt:1.146	Tue Nov 28 13:59:25 2006
+++ llvm/lib/Target/X86/README.txt	Sun Dec 10 19:20:25 2006
@@ -430,16 +430,13 @@
 We currently generate this code with llvmgcc4:
 
 _pairtest:
-        subl $12, %esp
-        movl 20(%esp), %eax
-        movl %eax, 4(%esp)
-        movl 16(%esp), %eax
-        movl %eax, (%esp)
-        movss (%esp), %xmm0
-        addss 4(%esp), %xmm0
-        movl 24(%esp), %eax
-        movss %xmm0, (%eax)
-        addl $12, %esp
+        movl 8(%esp), %eax
+        movl 4(%esp), %ecx
+        movd %eax, %xmm0
+        movd %ecx, %xmm1
+        addss %xmm0, %xmm1
+        movl 12(%esp), %eax
+        movss %xmm1, (%eax)
         ret
 
 we should be able to generate:
@@ -455,6 +452,10 @@
 a single 32-bit integer stack slot.  We should handle the safe cases above much
 nicer, while still handling the hard cases.
 
+While true in general, in this specific case we could do better by promoting
+load int + bitcast to float -> load fload.  This basically needs alignment info,
+the code is already implemented (but disabled) in dag combine).
+
 //===---------------------------------------------------------------------===//
 
 Another instruction selector deficiency: