Cycles: More workarounds for weird crashes on AVX2

Oh man, is it a compiler bug? Is it something we do stupid?

For now more crap to prevent crashes. During the conference will talk to
Maxyn about how can we troubleshoot such weird issues.
This commit is contained in:
Sergey Sharybin 2016-10-27 12:51:03 +02:00
parent 7e380ad4c0
commit f11298692b
2 changed files with 9 additions and 5 deletions

@ -591,7 +591,8 @@ ccl_device_inline float len_squared(const float4& a)
ccl_device_inline float3 normalize(const float3& a)
{
#if defined(__KERNEL_SSE41__) && defined(__KERNEL_SSE__)
/* TODO(sergey): Disabled for now, causes crashes in certain cases. */
#if defined(__KERNEL_SSE41__) && defined(__KERNEL_SSE__) && 0
__m128 norm = _mm_sqrt_ps(_mm_dp_ps(a.m128, a.m128, 0x7F));
return _mm_div_ps(a.m128, norm);
#else
@ -792,7 +793,8 @@ ccl_device_inline float4 operator-(const float4& a)
ccl_device_inline float4 operator*(const float4& a, const float4& b)
{
#ifdef __KERNEL_SSE__
/* TODO(sergey): Disabled for now, causes crashes in certain cases. */
#if defined(__KERNEL_SSE__) && 0
return _mm_mul_ps(a.m128, b.m128);
#else
return make_float4(a.x*b.x, a.y*b.y, a.z*b.z, a.w*b.w);
@ -840,7 +842,8 @@ ccl_device_inline float4 operator/(const float4& a, const float4& b)
ccl_device_inline float4 operator+(const float4& a, const float4& b)
{
#ifdef __KERNEL_SSE__
/* TODO(sergey): Disabled for now, causes crashes in certain cases. */
#if defined(__KERNEL_SSE__) && 0
return _mm_add_ps(a.m128, b.m128);
#else
return make_float4(a.x+b.x, a.y+b.y, a.z+b.z, a.w+b.w);

@ -74,7 +74,7 @@ ccl_device_inline float3 transform_perspective(const Transform *t, const float3
ccl_device_inline float3 transform_point(const Transform *t, const float3 a)
{
/* TODO(sergey): Disabled for now, causes crashes in certain cases. */
#if defined(__KERNEL_SSE__) && defined(__KERNEL_SSE2__)
#if defined(__KERNEL_SSE__) && defined(__KERNEL_SSE2__) && 0
ssef x, y, z, w, aa;
aa = a.m128;
@ -103,7 +103,8 @@ ccl_device_inline float3 transform_point(const Transform *t, const float3 a)
ccl_device_inline float3 transform_direction(const Transform *t, const float3 a)
{
#if defined(__KERNEL_SSE__) && defined(__KERNEL_SSE2__)
/* TODO(sergey): Disabled for now, causes crashes in certain cases. */
#if defined(__KERNEL_SSE__) && defined(__KERNEL_SSE2__) && 0
ssef x, y, z, w, aa;
aa = a.m128;
x = _mm_loadu_ps(&t->x.x);