diff options
Diffstat (limited to 'lib/Target/README.txt')
| -rw-r--r-- | lib/Target/README.txt | 80 |
1 files changed, 37 insertions, 43 deletions
diff --git a/lib/Target/README.txt b/lib/Target/README.txt index e1772c2..a6e05fa 100644 --- a/lib/Target/README.txt +++ b/lib/Target/README.txt @@ -106,7 +106,17 @@ Shrink: (setlt (loadi32 P), 0) -> (setlt (loadi8 Phi), 0) //===---------------------------------------------------------------------===// -Reassociate should turn: X*X*X*X -> t=(X*X) (t*t) to eliminate a multiply. +Reassociate should turn things like: + +int factorial(int X) { + return X*X*X*X*X*X*X*X; +} + +into llvm.powi calls, allowing the code generator to produce balanced +multiplication trees. + +First, the intrinsic needs to be extended to support integers, and second the +code generator needs to be enhanced to lower these to multiplication trees. //===---------------------------------------------------------------------===// @@ -119,7 +129,32 @@ int foo(int z, int n) { return bar(z, n) + bar(2*z, 2*n); } -Reassociate should handle the example in GCC PR16157. +This is blocked on not handling X*X*X -> powi(X, 3) (see note above). The issue +is that we end up getting t = 2*X s = t*t and don't turn this into 4*X*X, +which is the same number of multiplies and is canonical, because the 2*X has +multiple uses. Here's a simple example: + +define i32 @test15(i32 %X1) { + %B = mul i32 %X1, 47 ; X1*47 + %C = mul i32 %B, %B + ret i32 %C +} + + +//===---------------------------------------------------------------------===// + +Reassociate should handle the example in GCC PR16157: + +extern int a0, a1, a2, a3, a4; extern int b0, b1, b2, b3, b4; +void f () { /* this can be optimized to four additions... */ + b4 = a4 + a3 + a2 + a1 + a0; + b3 = a3 + a2 + a1 + a0; + b2 = a2 + a1 + a0; + b1 = a1 + a0; +} + +This requires reassociating to forms of expressions that are already available, +something that reassoc doesn't think about yet. //===---------------------------------------------------------------------===// @@ -721,47 +756,6 @@ be done safely if "b" isn't modified between the strlen and memcpy of course. //===---------------------------------------------------------------------===// -Reassociate should turn things like: - -int factorial(int X) { - return X*X*X*X*X*X*X*X; -} - -into llvm.powi calls, allowing the code generator to produce balanced -multiplication trees. - -//===---------------------------------------------------------------------===// - -We generate a horrible libcall for llvm.powi. For example, we compile: - -#include <cmath> -double f(double a) { return std::pow(a, 4); } - -into: - -__Z1fd: - subl $12, %esp - movsd 16(%esp), %xmm0 - movsd %xmm0, (%esp) - movl $4, 8(%esp) - call L___powidf2$stub - addl $12, %esp - ret - -GCC produces: - -__Z1fd: - subl $12, %esp - movsd 16(%esp), %xmm0 - mulsd %xmm0, %xmm0 - mulsd %xmm0, %xmm0 - movsd %xmm0, (%esp) - fldl (%esp) - addl $12, %esp - ret - -//===---------------------------------------------------------------------===// - We compile this program: (from GCC PR11680) http://gcc.gnu.org/bugzilla/attachment.cgi?id=4487 |
