i386: Split lea into shorter left shift by 2 or 3 bits with -Oz.

This patch avoids long lea instructions for performing x<<2 and x<<3
by splitting them into shorter sal and move (or xchg instructions).
Because this increases the number of instructions, but reduces the
total size, its suitable for -Oz (but not -Os).

The impact can be seen in the new test case:

int foo(int x) { return x<<2; }
int bar(int x) { return x<<3; }
long long fool(long long x) { return x<<2; }
long long barl(long long x) { return x<<3; }

where with -O2 we generate:

foo:	lea    0x0(,%rdi,4),%eax	// 7 bytes
	retq
bar:	lea    0x0(,%rdi,8),%eax	// 7 bytes
	retq
fool:	lea    0x0(,%rdi,4),%rax	// 8 bytes
	retq
barl:	lea    0x0(,%rdi,8),%rax	// 8 bytes
	retq

and with -Oz we now generate:

foo:	xchg   %eax,%edi		// 1 byte
	shl    $0x2,%eax		// 3 bytes
	retq
bar:	xchg   %eax,%edi		// 1 byte
	shl    $0x3,%eax		// 3 bytes
	retq
fool:	xchg   %rax,%rdi		// 2 bytes
	shl    $0x2,%rax		// 4 bytes
	retq
barl:	xchg   %rax,%rdi		// 2 bytes
	shl    $0x3,%rax		// 4 bytes
	retq

Over the entirety of the CSiBE code size benchmark this saves 1347
bytes (0.037%) for x86_64, and 1312 bytes (0.036%) with -m32.
Conveniently, there's already a backend function in i386.cc for
deciding whether to split an lea into its component instructions,
ix86_avoid_lea_for_addr, all that's required is an additional
clause checking for -Oz (i.e. optimize_size > 1).

2023-10-06  Roger Sayle  <roger@nextmovesoftware.com>
	    Uros Bizjak  <ubizjak@gmail.com>

gcc/ChangeLog
	* config/i386/i386.cc (ix86_avoid_lea_for_addr): Split LEAs used
	to perform left shifts into shorter instructions with -Oz.

gcc/testsuite/ChangeLog
	* gcc.target/i386/lea-2.c: New test case.

diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index 477e6cecc382987895a35efec539b39fcf5c4891..9557bffd092e52cf8e3d48cf0d27adb837e1b34b 100644 (file)
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -15543,6 +15543,13 @@ ix86_avoid_lea_for_addr (rtx_insn *insn, rtx operands[])
       && (regno0 == regno1 || regno0 == regno2))
     return true;
 
+  /* Split with -Oz if the encoding requires fewer bytes.  */
+  if (optimize_size > 1
+      && parts.scale > 1
+      && !parts.base
+      && (!parts.disp || parts.disp == const0_rtx)) 
+    return true;
+
   /* Check we need to optimize.  */
   if (!TARGET_AVOID_LEA_FOR_ADDR || optimize_function_for_size_p (cfun))
     return false;

diff --git a/gcc/testsuite/gcc.target/i386/lea-2.c b/gcc/testsuite/gcc.target/i386/lea-2.c
new file mode 100644 (file)
index 0000000..e9f12d7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/lea-2.c
@@ -0,0 +1,7 @@
+/* { dg-do compile } */
+/* { dg-options "-Oz" } */
+int foo(int x) { return x<<2; }
+int bar(int x) { return x<<3; }
+long long fool(long long x) { return x<<2; }
+long long barl(long long x) { return x<<3; }
+/* { dg-final { scan-assembler-not "lea\[lq\]" } } */