Only fixed stack objects and spill slots should be get FixedStack PseudoSourceValue.

[oota-llvm.git] / lib / Target / PowerPC / README.txt

diff --git a/lib/Target/PowerPC/README.txt b/lib/Target/PowerPC/README.txt
index 7bc50e5aa39d87dcc8e835a10b5acbb379102d7c..f5e50fc808a8d87ebe3547e0c5d3eaa2a5c20df6 100644 (file)
--- a/lib/Target/PowerPC/README.txt
+++ b/lib/Target/PowerPC/README.txt
@@ -3,7 +3,6 @@
 TODO:
 * gpr0 allocation
 * implement do-loop -> bdnz transform
-* Implement __builtin_trap (ISD::TRAP) as 'tw 31, 0, 0' aka 'trap'.
 * lmw/stmw pass a la arm load store optimizer for prolog/epilog
 
 ===-------------------------------------------------------------------------===
@@ -150,7 +149,7 @@ http://gcc.gnu.org/ml/gcc-patches/2006-02/msg00133.html
 
 Implement Newton-Rhapson method for improving estimate instructions to the
 correct accuracy, and implementing divide as multiply by reciprocal when it has
-more than one use.  Itanium will want this too.
+more than one use.  Itanium would want this too.
 
 ===-------------------------------------------------------------------------===
 
@@ -181,6 +180,16 @@ void bar() { struct foo R = { 1.0, 2.0 }; xxx(R); }
 
 ===-------------------------------------------------------------------------===
 
+Darwin Stub removal:
+
+We still generate calls to foo$stub, and stubs, on Darwin.  This is not
+necessary when building with the Leopard (10.5) or later linker, as stubs are
+generated by ld when necessary.  Parameterizing this based on the deployment
+target (-mmacosx-version-min) is probably enough.  x86-32 does this right, see
+its logic.
+
+===-------------------------------------------------------------------------===
+
 Darwin Stub LICM optimization:
 
 Loops like this:
@@ -714,3 +723,87 @@ GCC compiles this into:
 which is more efficient and can use mfocr.  See PR642 for some more context.
 
 //===---------------------------------------------------------------------===//
+
+void foo(float *data, float d) {
+   long i;
+   for (i = 0; i < 8000; i++)
+      data[i] = d;
+}
+void foo2(float *data, float d) {
+   long i;
+   data--;
+   for (i = 0; i < 8000; i++) {
+      data[1] = d;
+      data++;
+   }
+}
+
+These compile to:
+
+_foo:
+       li r2, 0
+LBB1_1:        ; bb
+       addi r4, r2, 4
+       stfsx f1, r3, r2
+       cmplwi cr0, r4, 32000
+       mr r2, r4
+       bne cr0, LBB1_1 ; bb
+       blr 
+_foo2:
+       li r2, 0
+LBB2_1:        ; bb
+       addi r4, r2, 4
+       stfsx f1, r3, r2
+       cmplwi cr0, r4, 32000
+       mr r2, r4
+       bne cr0, LBB2_1 ; bb
+       blr 
+
+The 'mr' could be eliminated to folding the add into the cmp better.
+
+//===---------------------------------------------------------------------===//
+Codegen for the following (low-probability) case deteriorated considerably 
+when the correctness fixes for unordered comparisons went in (PR 642, 58871).
+It should be possible to recover the code quality described in the comments.
+
+; RUN: llvm-as < %s | llc -march=ppc32  | grep or | count 3
+; This should produce one 'or' or 'cror' instruction per function.
+
+; RUN: llvm-as < %s | llc -march=ppc32  | grep mfcr | count 3
+; PR2964
+
+define i32 @test(double %x, double %y) nounwind  {
+entry:
+       %tmp3 = fcmp ole double %x, %y          ; <i1> [#uses=1]
+       %tmp345 = zext i1 %tmp3 to i32          ; <i32> [#uses=1]
+       ret i32 %tmp345
+}
+
+define i32 @test2(double %x, double %y) nounwind  {
+entry:
+       %tmp3 = fcmp one double %x, %y          ; <i1> [#uses=1]
+       %tmp345 = zext i1 %tmp3 to i32          ; <i32> [#uses=1]
+       ret i32 %tmp345
+}
+
+define i32 @test3(double %x, double %y) nounwind  {
+entry:
+       %tmp3 = fcmp ugt double %x, %y          ; <i1> [#uses=1]
+       %tmp34 = zext i1 %tmp3 to i32           ; <i32> [#uses=1]
+       ret i32 %tmp34
+}
+//===----------------------------------------------------------------------===//
+; RUN: llvm-as < %s | llc -march=ppc32 | not grep fneg
+
+; This could generate FSEL with appropriate flags (FSEL is not IEEE-safe, and 
+; should not be generated except with -enable-finite-only-fp-math or the like).
+; With the correctness fixes for PR642 (58871) LowerSELECT_CC would need to
+; recognize a more elaborate tree than a simple SETxx.
+
+define double @test_FNEG_sel(double %A, double %B, double %C) {
+        %D = sub double -0.000000e+00, %A               ; <double> [#uses=1]
+        %Cond = fcmp ugt double %D, -0.000000e+00               ; <i1> [#uses=1]
+        %E = select i1 %Cond, double %B, double %C              ; <double> [#uses=1]
+        ret double %E
+}
+