Replace r169459 with something safer. Rather than having computeMaskedBits to

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

diff --git a/lib/Target/ARM/README-Thumb.txt b/lib/Target/ARM/README-Thumb.txt
index 8ffe0b17a555ba6da6d60add7b0d29702fe20873..463c440852f56c573fe2983cda2634bd862748bb 100644 (file)
--- a/lib/Target/ARM/README-Thumb.txt
+++ b/lib/Target/ARM/README-Thumb.txt
@@ -37,7 +37,7 @@ LPCRELL0:
        mov r1, #PCRELV0
        add r1, pc
        ldr r0, [r0, r1]
-       cpy pc, r0 
+       mov pc, r0 
        .align  2
 LJTI1_0_0:
        .long    LBB1_3
@@ -51,7 +51,7 @@ We should be able to generate:
 LPCRELL0:
        add r1, LJTI1_0_0
        ldr r0, [r0, r1]
-       cpy pc, r0 
+       mov pc, r0 
        .align  2
 LJTI1_0_0:
        .long    LBB1_3
@@ -68,7 +68,7 @@ LPCRELL0:
 
 //===---------------------------------------------------------------------===//
 
-We compiles the following:
+We compile the following:
 
 define i16 @func_entry_2E_ce(i32 %i) {
         switch i32 %i, label %bb12.exitStub [
@@ -196,14 +196,6 @@ This is especially bad when dynamic alloca is used. The all fixed size stack
 objects are referenced off the frame pointer with negative offsets. See
 oggenc for an example.
 
-//===---------------------------------------------------------------------===//
-
-We are reserving R3 as a scratch register under thumb mode. So if it is live in
-to the function, we save / restore R3 to / from R12. Until register scavenging
-is done, we should save R3 to a high callee saved reg at emitPrologue time
-(when hasFP is true or stack size is large) and restore R3 from that register
-instead. This allows us to at least get rid of the save to r12 everytime it is
-used.
 
 //===---------------------------------------------------------------------===//
 
@@ -214,8 +206,8 @@ LPC0:
        add r5, pc
        ldr r6, LCPI1_1
        ldr r2, LCPI1_2
-       cpy r3, r6
-       cpy lr, pc
+       mov r3, r6
+       mov lr, pc
        bx r5
 
 //===---------------------------------------------------------------------===//
@@ -245,11 +237,31 @@ Make use of hi register variants of cmp: tCMPhir / tCMPZhir.
 
 //===---------------------------------------------------------------------===//
 
-Rather than generating ldrsb, sometimes it's better to select to ldrb + sxtb.
-The problem is ldrsb addressing mode [r, r] means the zero offset requires an
-extra move. e.g. ldr_ext.ll test3:
-       movs r1, #0
-       ldrsb r0, [r0, r1]
-=>
-       ldrb    r0, [r0, #0]
-       sxtb    r0, r0
+Thumb1 immediate field sometimes keep pre-scaled values. See
+Thumb1RegisterInfo::eliminateFrameIndex. This is inconsistent from ARM and
+Thumb2.
+
+//===---------------------------------------------------------------------===//
+
+Rather than having tBR_JTr print a ".align 2" and constant island pass pad it,
+add a target specific ALIGN instruction instead. That way, GetInstSizeInBytes
+won't have to over-estimate. It can also be used for loop alignment pass.
+
+//===---------------------------------------------------------------------===//
+
+We generate conditional code for icmp when we don't need to. This code:
+
+  int foo(int s) {
+    return s == 1;
+  }
+
+produces:
+
+foo:
+        cmp     r0, #1
+        mov.w   r0, #0
+        it      eq
+        moveq   r0, #1
+        bx      lr
+
+when it could use subs + adcs. This is GCC PR46975.