X-Git-Url: http://plrg.eecs.uci.edu/git/?a=blobdiff_plain;f=lib%2FCodeGen%2FREADME.txt;h=7f75f65167a382b515f79f547f2988ba06a66564;hb=1b3f9198ab3880be34b6252423b9e388b5cd6a5e;hp=d5ddd217962100d8b2c0c70e867dee3ae9282d64;hpb=877333b99dd830c3e8bb7eaa1345ea942d29fc06;p=oota-llvm.git

diff --git a/lib/CodeGen/README.txt b/lib/CodeGen/README.txt
index d5ddd217962..7f75f65167a 100644
--- a/lib/CodeGen/README.txt
+++ b/lib/CodeGen/README.txt
@@ -26,45 +26,7 @@ and then "merge" mul and mov:
         sxth r3, r3
         mla r4, r3, lr, r4
 
-It also increase the likelyhood the store may become dead.
-
-//===---------------------------------------------------------------------===//
-
-I think we should have a "hasSideEffects" flag (which is automatically set for
-stuff that "isLoad" "isCall" etc), and the remat pass should eventually be able
-to remat any instruction that has no side effects, if it can handle it and if
-profitable.
-
-For now, I'd suggest having the remat stuff work like this:
-
-1. I need to spill/reload this thing.
-2. Check to see if it has side effects.
-3. Check to see if it is simple enough: e.g. it only has one register
-destination and no register input.
-4. If so, clone the instruction, do the xform, etc.
-
-Advantages of this are:
-
-1. the .td file describes the behavior of the instructions, not the way the
-   algorithm should work.
-2. as remat gets smarter in the future, we shouldn't have to be changing the .td
-   files.
-3. it is easier to explain what the flag means in the .td file, because you
-   don't have to pull in the explanation of how the current remat algo works.
-
-Some potential added complexities:
-
-1. Some instructions have to be glued to it's predecessor or successor. All of
-   the PC relative instructions and condition code setting instruction. We could
-   mark them as hasSideEffects, but that's not quite right. PC relative loads
-   from constantpools can be remat'ed, for example. But it requires more than
-   just cloning the instruction. Some instructions can be remat'ed but it
-   expands to more than one instruction. But allocator will have to make a
-   decision.
-
-4. As stated in 3, not as simple as cloning in some cases. The target will have
-   to decide how to remat it. For example, an ARM 2-piece constant generation
-   instruction is remat'ed as a load from constantpool.
+It also increase the likelihood the store may become dead.
 
 //===---------------------------------------------------------------------===//
 
@@ -87,14 +49,14 @@ scheduled after any node that reads %reg1039.
 
 Use local info (i.e. register scavenger) to assign it a free register to allow
 reuse:
-	ldr r3, [sp, #+4]
-	add r3, r3, #3
-	ldr r2, [sp, #+8]
-	add r2, r2, #2
-	ldr r1, [sp, #+4]  <==
-	add r1, r1, #1
-	ldr r0, [sp, #+4]
-	add r0, r0, #2
+        ldr r3, [sp, #+4]
+        add r3, r3, #3
+        ldr r2, [sp, #+8]
+        add r2, r2, #2
+        ldr r1, [sp, #+4]  <==
+        add r1, r1, #1
+        ldr r0, [sp, #+4]
+        add r0, r0, #2
 
 //===---------------------------------------------------------------------===//
 
@@ -200,9 +162,38 @@ synthesize the various copy insertion/inspection methods in TargetInstrInfo.
 
 //===---------------------------------------------------------------------===//
 
-Stack coloring improvments:
+Stack coloring improvements:
 
 1. Do proper LiveStackAnalysis on all stack objects including those which are
    not spill slots.
 2. Reorder objects to fill in gaps between objects.
    e.g. 4, 1, <gap>, 4, 1, 1, 1, <gap>, 4 => 4, 1, 1, 1, 1, 4, 4
+
+//===---------------------------------------------------------------------===//
+
+The scheduler should be able to sort nearby instructions by their address. For
+example, in an expanded memset sequence it's not uncommon to see code like this:
+
+  movl $0, 4(%rdi)
+  movl $0, 8(%rdi)
+  movl $0, 12(%rdi)
+  movl $0, 0(%rdi)
+
+Each of the stores is independent, and the scheduler is currently making an
+arbitrary decision about the order.
+
+//===---------------------------------------------------------------------===//
+
+Another opportunitiy in this code is that the $0 could be moved to a register:
+
+  movl $0, 4(%rdi)
+  movl $0, 8(%rdi)
+  movl $0, 12(%rdi)
+  movl $0, 0(%rdi)
+
+This would save substantial code size, especially for longer sequences like
+this. It would be easy to have a rule telling isel to avoid matching MOV32mi
+if the immediate has more than some fixed number of uses. It's more involved
+to teach the register allocator how to do late folding to recover from
+excessive register pressure.
+