Clamp input scalar value to range [-10, +10] to avoid precision problems
when the absolute value of input is too large.
Fixes dEQP-GLES3.functional.shaders.builtin_functions.precision.tanh.* test
failures.
v2: added more explanation in the comment.
v3: fixed a typo in the comment.
Signed-off-by: Haixia Shi <h...@chromium.org>
Cc: Jason Ekstrand <ja...@jlekstrand.net>,
Cc: Stéphane Marchesin <marc...@chromium.org>,
Cc: Kenneth Graunke <kenn...@whitecape.org>
Change-Id: I324c948b3323ff8107127c42934f14459e124b95
---
src/compiler/glsl/builtin_functions.cpp | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
diff --git a/src/compiler/glsl/builtin_functions.cpp
b/src/compiler/glsl/builtin_functions.cpp
index 3e4bcbb..0bacffb 100644
--- a/src/compiler/glsl/builtin_functions.cpp
+++ b/src/compiler/glsl/builtin_functions.cpp
@@ -3563,9 +3563,18 @@ builtin_builder::_tanh(const glsl_type *type)
ir_variable *x = in_var(type, "x");
MAKE_SIG(type, v130, 1, x);
+ /*
+ * Clamp x to [-10, +10] to avoid precision problems.
+ * When x > 10, e^(-x) is so small relative to e^x that it gets flushed to
+ * zero in the computation e^x + e^(-x). The same happens in the other
+ * direction when x < -10.
+ */
+ ir_variable *t = body.make_temp(type, "tmp");
+ body.emit(assign(t, min2(max2(x, imm(-10.0f)), imm(10.0f))));
+
/* (e^x - e^(-x)) / (e^x + e^(-x)) */
- body.emit(ret(div(sub(exp(x), exp(neg(x))),
- add(exp(x), exp(neg(x))))));
+ body.emit(ret(div(sub(exp(t), exp(neg(t))),
+ add(exp(t), exp(neg(t))))));
return sig;
}
--
2.8.0.rc3.226.g39d4020
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
