Ah OK. But presumably the gather4_po variant is chosen when the constant offsets are outside the -8..7 range, since I didn't get any failures, and the test suite has checks around impl-defined min/maxes... Could be that all those were the non-const variants. Looking through the brw_fs code, I indeed don't see anything for promoting SHADER_OPCODE_TG4_LOGICAL into SHADER_OPCODE_TG4_OFFSET_LOGICAL. But that code is subtle, so perhaps it's handled somewhere I didn't notice.
-ilia On Sun, Nov 27, 2016 at 5:37 PM, Chris Forbes <[email protected]> wrote: > The HW limits here are -8/7 when using the gather4 message. [gather4_po > allows -32/31, and specified per channel] > > On Mon, Nov 28, 2016 at 10:49 AM, Ilia Mirkin <[email protected]> wrote: >> >> This matches what NVIDIA and AMD hardware expose. >> >> Signed-off-by: Ilia Mirkin <[email protected]> >> --- >> >> Not sure what the true HW limit is here. On NVIDIA, the true HW limit >> really >> is -32/31 though. As an aside, according to vulkan.gpuinfo.org, the Intel >> Windows driver also exposes -32/31. >> >> With the updated limits on SKL, everything still passes: >> >> ./deqp-vk --deqp-visibility=hidden --deqp-case='*texture_gather*' >> Test run totals: >> Passed: 762/1524 (50.0%) >> Failed: 0/1524 (0.0%) >> Not supported: 762/1524 (50.0%) >> Warnings: 0/1524 (0.0%) >> >> src/intel/vulkan/anv_device.c | 4 ++-- >> 1 file changed, 2 insertions(+), 2 deletions(-) >> >> diff --git a/src/intel/vulkan/anv_device.c b/src/intel/vulkan/anv_device.c >> index 16aba59..d20dc0f 100644 >> --- a/src/intel/vulkan/anv_device.c >> +++ b/src/intel/vulkan/anv_device.c >> @@ -555,8 +555,8 @@ void anv_GetPhysicalDeviceProperties( >> .minStorageBufferOffsetAlignment = 1, >> .minTexelOffset = -8, >> .maxTexelOffset = 7, >> - .minTexelGatherOffset = -8, >> - .maxTexelGatherOffset = 7, >> + .minTexelGatherOffset = -32, >> + .maxTexelGatherOffset = 31, >> .minInterpolationOffset = -0.5, >> .maxInterpolationOffset = 0.4375, >> .subPixelInterpolationOffsetBits = 4, >> -- >> 2.7.3 >> >> _______________________________________________ >> mesa-dev mailing list >> [email protected] >> https://lists.freedesktop.org/mailman/listinfo/mesa-dev > > _______________________________________________ mesa-dev mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/mesa-dev
