Hello!
Attached patch introduces ROUND_UP and ROUND_DOWN global macros.
These come handy to round and align various values, as shown by the
usage in config/i386/ files.
In addition to target independent code, many targets could benefit
from these universal macros (e.g. arm and aarch64 can immediately
replace their equivalent local definitions), so I propose to put these
definitions to be available globally throughout the source. From a
quick look, there are a number of places these macro can be used.
And, as witnessed in attached patch, it is soooo easy to forget those "-1"s:
- offset = (offset + stack_alignment_needed) & -stack_alignment_needed;
+ offset = ROUND_UP (offset, stack_alignment_needed);
[...]
- offset = (offset + stack_alignment_needed - 1) & -stack_alignment_needed;
+ offset = ROUND_UP (offset, stack_alignment_needed);
2015-10-02 Uros Bizjak <ubiz...@gmail.com>
* system.h (ROUND_UP): New macro definition.
(ROUND_DOWN): Ditto.
* ggc-page.c (ROUND_UP): Remove local macro definition.
(PAGE_ALIGN): Implement using ROUND_UP macro.
* config/i386/i386.h (PUSH_ROUNDING): Implement using ROUND_UP macro.
* config/i386/i386.c (function_arg_advance_64): Use ROUND_UP macro
to align values.
(ix86_compute_frame_layout): Ditto.
(ix86_expand_prologue): Ditto.
(ix86_adjust_stack_and_probe): Use ROUND_DOWN macro to round
down values.
(expand_set_or_movmem_via_rep): Ditto.
Patch was bootstrapped and regression tested on x86_64-linux-gnu {,-m32}.
OK for mainline?
Uros.
Index: ggc-page.c
===================================================================
--- ggc-page.c (revision 228380)
+++ ggc-page.c (working copy)
@@ -216,13 +216,9 @@ static const size_t extra_order_size_table[] = {
#define ROUND_UP_VALUE(x, f) ((f) - 1 - ((f) - 1 + (x)) % (f))
-/* Compute the smallest multiple of F that is >= X. */
-
-#define ROUND_UP(x, f) (CEIL (x, f) * (f))
-
/* Round X to next multiple of the page size */
-#define PAGE_ALIGN(x) (((x) + G.pagesize - 1) & ~(G.pagesize - 1))
+#define PAGE_ALIGN(x) ROUND_UP ((x), G.pagesize)
/* The Ith entry is the number of objects on a page or order I. */
Index: system.h
===================================================================
--- system.h (revision 228380)
+++ system.h (working copy)
@@ -369,6 +369,12 @@ extern int errno;
/* Returns the least number N such that N * Y >= X. */
#define CEIL(x,y) (((x) + (y) - 1) / (y))
+/* This macro rounds x up to the y boundary. */
+#define ROUND_UP(x,y) (((x) + (y) - 1) & ~((y) - 1))
+
+/* This macro rounds x down to the y boundary. */
+#define ROUND_DOWN(x,y) ((x) & ~((y) - 1))
+
#ifdef HAVE_SYS_WAIT_H
#include <sys/wait.h>
#endif
Index: config/i386/i386.h
===================================================================
--- config/i386/i386.h (revision 228380)
+++ config/i386/i386.h (working copy)
@@ -1596,8 +1596,7 @@ enum reg_class
and -8 for 64bit targets, we need to make sure all stack pointer adjustments
are in multiple of 4 for 32bit targets and 8 for 64bit targets. */
-#define PUSH_ROUNDING(BYTES) \
- (((BYTES) + UNITS_PER_WORD - 1) & -UNITS_PER_WORD)
+#define PUSH_ROUNDING(BYTES) ROUND_UP (BYTES, UNITS_PER_WORD)
/* If defined, the maximum amount of space required for outgoing arguments
will be computed and placed into the variable `crtl->outgoing_args_size'.
Index: config/i386/i386.c
===================================================================
--- config/i386/i386.c (revision 228380)
+++ config/i386/i386.c (working copy)
@@ -8651,7 +8651,7 @@ function_arg_advance_64 (CUMULATIVE_ARGS *cum, mac
else
{
int align = ix86_function_arg_boundary (mode, type) / BITS_PER_WORD;
- cum->words = (cum->words + align - 1) & ~(align - 1);
+ cum->words = ROUND_UP (cum->words, align);
cum->words += words;
return 0;
}
@@ -11285,7 +11285,7 @@ ix86_compute_frame_layout (struct ix86_frame *fram
16-byte aligned default stack, and thus we don't need to be
within the re-aligned local stack frame to save them. */
gcc_assert (INCOMING_STACK_BOUNDARY >= 128);
- offset = (offset + 16 - 1) & -16;
+ offset = ROUND_UP (offset, 16);
offset += frame->nsseregs * 16;
}
frame->sse_reg_save_offset = offset;
@@ -11295,7 +11295,7 @@ ix86_compute_frame_layout (struct ix86_frame *fram
sure that no value happens to be the same before and after, force
the alignment computation below to add a non-zero value. */
if (stack_realign_fp)
- offset = (offset + stack_alignment_needed) & -stack_alignment_needed;
+ offset = ROUND_UP (offset, stack_alignment_needed);
/* Va-arg area */
frame->va_arg_size = ix86_varargs_gpr_size + ix86_varargs_fpr_size;
@@ -11308,7 +11308,7 @@ ix86_compute_frame_layout (struct ix86_frame *fram
|| !crtl->is_leaf
|| cfun->calls_alloca
|| ix86_current_function_calls_tls_descriptor)
- offset = (offset + stack_alignment_needed - 1) & -stack_alignment_needed;
+ offset = ROUND_UP (offset, stack_alignment_needed);
/* Frame pointer points here. */
frame->frame_pointer_offset = offset;
@@ -11334,7 +11334,7 @@ ix86_compute_frame_layout (struct ix86_frame *fram
or using alloca. */
if (!crtl->is_leaf || cfun->calls_alloca
|| ix86_current_function_calls_tls_descriptor)
- offset = (offset + preferred_alignment - 1) & -preferred_alignment;
+ offset = ROUND_UP (offset, preferred_alignment);
/* We've reached end of stack frame. */
frame->stack_pointer_offset = offset;
@@ -12050,7 +12050,7 @@ ix86_adjust_stack_and_probe (const HOST_WIDE_INT s
/* Step 1: round SIZE to the previous multiple of the interval. */
- rounded_size = size & -PROBE_INTERVAL;
+ rounded_size = ROUND_DOWN (size, PROBE_INTERVAL);
/* Step 2: compute initial and final value of the loop counter. */
@@ -12204,7 +12204,7 @@ ix86_emit_probe_stack_range (HOST_WIDE_INT first,
/* Step 1: round SIZE to the previous multiple of the interval. */
- rounded_size = size & -PROBE_INTERVAL;
+ rounded_size = ROUND_DOWN (size, PROBE_INTERVAL);
/* Step 2: compute initial and final value of the loop counter. */
@@ -12663,7 +12663,7 @@ ix86_expand_prologue (void)
pointer is no longer valid. As for the value of sp_offset,
see ix86_compute_frame_layout, which we need to match in order
to pass verification of stack_pointer_offset at the end. */
- m->fs.sp_offset = (m->fs.sp_offset + align_bytes) & -align_bytes;
+ m->fs.sp_offset = ROUND_UP (m->fs.sp_offset, align_bytes);
m->fs.sp_valid = false;
}
@@ -24692,8 +24692,8 @@ expand_set_or_movmem_via_rep (rtx destmem, rtx src
destexp = gen_rtx_PLUS (Pmode, destptr, countreg);
if ((!issetmem || orig_value == const0_rtx) && CONST_INT_P (count))
{
- rounded_count = (INTVAL (count)
- & ~((HOST_WIDE_INT) GET_MODE_SIZE (mode) - 1));
+ rounded_count
+ = ROUND_DOWN (INTVAL (count), (HOST_WIDE_INT) GET_MODE_SIZE (mode));
destmem = shallow_copy_rtx (destmem);
set_mem_size (destmem, rounded_count);
}
@@ -24719,8 +24719,8 @@ expand_set_or_movmem_via_rep (rtx destmem, rtx src
srcexp = gen_rtx_PLUS (Pmode, srcptr, countreg);
if (CONST_INT_P (count))
{
- rounded_count = (INTVAL (count)
- & ~((HOST_WIDE_INT) GET_MODE_SIZE (mode) - 1));
+ rounded_count
+ = ROUND_DOWN (INTVAL (count), (HOST_WIDE_INT) GET_MODE_SIZE (mode));
srcmem = shallow_copy_rtx (srcmem);
set_mem_size (srcmem, rounded_count);
}
