Author: sampo
Date: Tue Nov 27 13:28:48 2007
New Revision: 44371
URL: http://llvm.org/viewvc/llvm-project?rev=44371&view=rev
Log:
Support returning non-power-of-2 vectors to unblock some work
Modified:
llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp
llvm/trunk/lib/Target/X86/X86CallingConv.td
Modified: llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp
URL:
http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp?rev=44371&r1=44370&r2=44371&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp (original)
+++ llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp Tue Nov 27 13:28:48
2007
@@ -364,6 +364,13 @@
unsigned NumVectorRegs = 1;
+ // FIXME: We don't support non-power-of-2-sized vectors for now. Ideally we
+ // could break down into LHS/RHS like LegalizeDAG does.
+ if (!isPowerOf2_32(NumElts)) {
+ NumVectorRegs = NumElts;
+ NumElts = 1;
+ }
+
// Divide the input until we get to a supported size. This will always
// end with a scalar if the target doesn't support vectors.
while (NumElts > 1 &&
Modified: llvm/trunk/lib/Target/X86/X86CallingConv.td
URL:
http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86CallingConv.td?rev=44371&r1=44370&r2=44371&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86CallingConv.td (original)
+++ llvm/trunk/lib/Target/X86/X86CallingConv.td Tue Nov 27 13:28:48 2007
@@ -52,10 +52,12 @@
// X86-32 FastCC return-value convention.
def RetCC_X86_32_Fast : CallingConv<[
- // The X86-32 fastcc returns FP values in XMM0 if the target has SSE2,
- // otherwise it is the the C calling conventions.
- CCIfType<[f32], CCIfSubtarget<"hasSSE2()", CCAssignToReg<[XMM0]>>>,
- CCIfType<[f64], CCIfSubtarget<"hasSSE2()", CCAssignToReg<[XMM0]>>>,
+ // The X86-32 fastcc returns 1, 2, or 3 FP values in XMM0-2 if the target has
+ // SSE2, otherwise it is the the C calling conventions.
+ // This can happen when a float, 2 x float, or 3 x float vector is split by
+ // target lowering, and is returned in 1-3 sse regs.
+ CCIfType<[f32], CCIfSubtarget<"hasSSE2()", CCAssignToReg<[XMM0,XMM1,XMM2]>>>,
+ CCIfType<[f64], CCIfSubtarget<"hasSSE2()", CCAssignToReg<[XMM0,XMM1,XMM2]>>>,
CCDelegateTo<RetCC_X86Common>
]>;
_______________________________________________
llvm-commits mailing list
[email protected]
http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits
