RemoveUnusedBrs: Allow less unconditional work and in particular division (#5989)

Fixes #5983: The testcase from there is used here in a new testcase
remove-unused-brs_levels in which we check if we are willing to unconditionally
do a division operation. Turning an if with an arm that does a division into a
select, which always does the division, is almost 5x slower, so we should probably
be extremely careful about doing that.

I took some measurements and have some suggestions for changes in this PR:

*   Raise the cost of div/rem to what I measure on my machine, which is 5x slower
    than an add, or worse.
*   For some reason we added the if arms rather than take the max of them, so
    fix that. This does not help the issue, but was confusing.
*   Adjust TooCostlyToRunUnconditionally in the pass from 9 to 8 (this helps
    balance the last point).
*   Use half that value when not optimizing for size. That is, we allow only 4 extra
    unconditional work normally, and 8 in -Os, and when -Oz then we allow any
    extra amount.

Aside from the new testcases, some existing ones changed. They all appear to
change in a reasonable way, to me.

We should perhaps go even further than this, and not even run a division
unconditionally in -Os, but I wasn't sure it makes sense to go that far as
other benchmarks may be affected. For now, this makes the benchmark in
#5983 run at full speed in -O3 or -Os, and it remains slow in -Oz. The
modified version of the benchmark that only divides in the if (no other
operations) is still fast in -O3, but it become slow in -Os as we do turn that
if into a select (but again, I didn't want to go that far as to overfit on that one
benchmark).

1 files changed, 18 insertions, 4 deletions

diff --git a/test/wasm2js/conversions-modified.2asm.js.opt b/test/wasm2js/conversions-modified.2asm.js.opt
index 811845f9d..5eb7435ee 100644
--- a/test/wasm2js/conversions-modified.2asm.js.opt
+++ b/test/wasm2js/conversions-modified.2asm.js.opt
@@ -121,15 +121,29 @@ function asmFunc(imports) {
  }
  
  function legalstub$7($0) {
-  i64toi32_i32$HIGH_BITS = Math_fround(Math_abs($0)) >= Math_fround(1.0) ? ~~($0 > Math_fround(0.0) ? Math_fround(Math_min(Math_fround(Math_floor(Math_fround($0 * Math_fround(2.3283064365386963e-10)))), Math_fround(4294967296.0))) : Math_fround(Math_ceil(Math_fround(Math_fround($0 - Math_fround(~~$0 >>> 0 >>> 0)) * Math_fround(2.3283064365386963e-10))))) >>> 0 : 0;
+  var $1 = 0, $2 = 0;
+  $2 = ~~$0 >>> 0;
+  if (Math_fround(Math_abs($0)) >= Math_fround(1.0)) {
+   $1 = ~~($0 > Math_fround(0.0) ? Math_fround(Math_min(Math_fround(Math_floor(Math_fround($0 * Math_fround(2.3283064365386963e-10)))), Math_fround(4294967296.0))) : Math_fround(Math_ceil(Math_fround(Math_fround($0 - Math_fround(~~$0 >>> 0 >>> 0)) * Math_fround(2.3283064365386963e-10))))) >>> 0
+  } else {
+   $1 = 0
+  }
+  i64toi32_i32$HIGH_BITS = $1;
   setTempRet0(i64toi32_i32$HIGH_BITS | 0);
-  return ~~$0 >>> 0;
+  return $2;
  }
  
  function legalstub$9($0) {
-  i64toi32_i32$HIGH_BITS = Math_abs($0) >= 1.0 ? ~~($0 > 0.0 ? Math_min(Math_floor($0 * 2.3283064365386963e-10), 4294967295.0) : Math_ceil(($0 - +(~~$0 >>> 0 >>> 0)) * 2.3283064365386963e-10)) >>> 0 : 0;
+  var $1 = 0, $2 = 0;
+  $2 = ~~$0 >>> 0;
+  if (Math_abs($0) >= 1.0) {
+   $1 = ~~($0 > 0.0 ? Math_min(Math_floor($0 * 2.3283064365386963e-10), 4294967295.0) : Math_ceil(($0 - +(~~$0 >>> 0 >>> 0)) * 2.3283064365386963e-10)) >>> 0
+  } else {
+   $1 = 0
+  }
+  i64toi32_i32$HIGH_BITS = $1;
   setTempRet0(i64toi32_i32$HIGH_BITS | 0);
-  return ~~$0 >>> 0;
+  return $2;
  }
  
  function legalstub$12($0, $1) {