- Remove Tilmann's custom truncate lowering: it completely hosed over
DAGcombine's ability to find reasons to remove truncates when they were not
needed. Consequently, the CellSPU backend would produce correct, but _really
slow and horrible_, code.
Replaced with instruction sequences that do the equivalent truncation in
SPUInstrInfo.td.
- Re-examine how unaligned loads and stores work. Generated unaligned
load code has been tested on the CellSPU hardware; see the i32operations.c
and i64operations.c in CodeGen/CellSPU/useful-harnesses. (While they may be
toy test code, it does prove that some real world code does compile
correctly.)
- Fix truncating stores in bug 3193 (note: unpack_df.ll will still make llc
fault because i64 ult is not yet implemented.)
- Added i64 eq and neq for setcc and select/setcc; started new instruction
information file for them in SPU64InstrInfo.td. Additional i64 operations
should be added to this file and not to SPUInstrInfo.td.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61447 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/Target/CellSPU/SPUOperands.td b/lib/Target/CellSPU/SPUOperands.td
index d788f83..802628f 100644
--- a/lib/Target/CellSPU/SPUOperands.td
+++ b/lib/Target/CellSPU/SPUOperands.td
@@ -609,15 +609,15 @@
let PrintMethod = "printSymbolLSA";
}
-// memory s7imm(reg) operaand
-def memri7 : Operand<iPTR> {
- let PrintMethod = "printMemRegImmS7";
+// Shuffle address memory operaand [s7imm(reg) d-format]
+def shufaddr : Operand<iPTR> {
+ let PrintMethod = "printShufAddr";
let MIOperandInfo = (ops s7imm:$imm, ptr_rc:$reg);
}
// memory s10imm(reg) operand
-def memri10 : Operand<iPTR> {
- let PrintMethod = "printMemRegImmS10";
+def dformaddr : Operand<iPTR> {
+ let PrintMethod = "printDFormAddr";
let MIOperandInfo = (ops s10imm:$imm, ptr_rc:$reg);
}