X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=lib%2FTarget%2FARM%2FREADME.txt;h=57dc6cb88bed483d42db746dc1a68a154a22f714;hb=1106660066504d163543607b38371c97aef7708e;hp=9fc3fb92cb2c1c4a7a7fc5062d1cfe5c590a8885;hpb=a10213e9341963e47008a697d9fb2f901e17f4dc;p=oota-llvm.git

diff --git a/lib/Target/ARM/README.txt b/lib/Target/ARM/README.txt
index 9fc3fb92cb2..57dc6cb88be 100644
--- a/lib/Target/ARM/README.txt
+++ b/lib/Target/ARM/README.txt
@@ -501,11 +501,6 @@ those operations and the ARMv6 scalar versions.
 
 //===---------------------------------------------------------------------===//
 
-ARM::MOVCCr is commutable (by flipping the condition). But we need to implement
-ARMInstrInfo::commuteInstruction() to support it.
-
-//===---------------------------------------------------------------------===//
-
 Split out LDR (literal) from normal ARM LDR instruction. Also consider spliting
 LDR into imm12 and so_reg forms. This allows us to clean up some code. e.g.
 ARMLoadStoreOptimizer does not need to look at LDR (literal) and LDR (so_reg)
@@ -657,3 +652,82 @@ Note that both "tst" and "moveq" are redundant.
 
 //===---------------------------------------------------------------------===//
 
+When loading immediate constants with movt/movw, if there are multiple
+constants needed with the same low 16 bits, and those values are not live at
+the same time, it would be possible to use a single movw instruction, followed
+by multiple movt instructions to rewrite the high bits to different values.
+For example:
+
+  volatile store i32 -1, i32* inttoptr (i32 1342210076 to i32*), align 4,
+  !tbaa
+!0
+  volatile store i32 -1, i32* inttoptr (i32 1342341148 to i32*), align 4,
+  !tbaa
+!0
+
+is compiled and optimized to:
+
+    movw    r0, #32796
+    mov.w    r1, #-1
+    movt    r0, #20480
+    str    r1, [r0]
+    movw    r0, #32796    @ <= this MOVW is not needed, value is there already
+    movt    r0, #20482
+    str    r1, [r0]
+
+//===---------------------------------------------------------------------===//
+
+Improve codegen for select's:
+if (x != 0) x = 1
+if (x == 1) x = 1
+
+ARM codegen used to look like this:
+       mov     r1, r0
+       cmp     r1, #1
+       mov     r0, #0
+       moveq   r0, #1
+
+The naive lowering select between two different values. It should recognize the
+test is equality test so it's more a conditional move rather than a select:
+       cmp     r0, #1
+       movne   r0, #0
+
+Currently this is a ARM specific dag combine. We probably should make it into a
+target-neutral one.
+
+//===---------------------------------------------------------------------===//
+
+Optimize unnecessary checks for zero with __builtin_clz/ctz.  Those builtins
+are specified to be undefined at zero, so portable code must check for zero
+and handle it as a special case.  That is unnecessary on ARM where those
+operations are implemented in a way that is well-defined for zero.  For
+example:
+
+int f(int x) { return x ? __builtin_clz(x) : sizeof(int)*8; }
+
+should just be implemented with a CLZ instruction.  Since there are other
+targets, e.g., PPC, that share this behavior, it would be best to implement
+this in a target-independent way: we should probably fold that (when using
+"undefined at zero" semantics) to set the "defined at zero" bit and have
+the code generator expand out the right code.
+
+
+//===---------------------------------------------------------------------===//
+
+Clean up the test/MC/ARM files to have more robust register choices.
+
+R0 should not be used as a register operand in the assembler tests as it's then
+not possible to distinguish between a correct encoding and a missing operand
+encoding, as zero is the default value for the binary encoder.
+e.g.,
+    add r0, r0  // bad
+    add r3, r5  // good
+
+Register operands should be distinct. That is, when the encoding does not
+require two syntactical operands to refer to the same register, two different
+registers should be used in the test so as to catch errors where the
+operands are swapped in the encoding.
+e.g.,
+    subs.w r1, r1, r1 // bad
+    subs.w r1, r2, r3 // good
+