On 01/22/2013 10:36 PM, Matt Turner wrote:
On Mon, Jan 21, 2013 at 12:49 AM, Chad Versace
chad.vers...@linux.intel.com wrote:
+ /**
+* \brief Lower a packSnorm2x16 expression.
+*
+* \param vec2_rval is packSnorm2x16's input
+* \return packSnorm2x16's output as a uint rvalue
+
On Wed, Jan 23, 2013 at 6:06 AM, Ian Romanick i...@freedesktop.org wrote:
On 01/22/2013 10:36 PM, Matt Turner wrote:
On Mon, Jan 21, 2013 at 12:49 AM, Chad Versace
chad.vers...@linux.intel.com wrote:
+ /**
+* \brief Lower a packSnorm2x16 expression.
+*
+* \param vec2_rval is
On 01/22/2013 07:36 PM, Matt Turner wrote:
On Mon, Jan 21, 2013 at 12:49 AM, Chad Versace
chad.vers...@linux.intel.com wrote:
Lower them to arithmetic and bit manipulation expressions.
v2:
- Rewrite using ir_builder. [for idr]
- In lowering packHalf2x16, don't truncate subnormal float16
On 01/22/2013 09:19 PM, Paul Berry wrote:
On 21 January 2013 00:49, Chad Versace chad.vers...@linux.intel.com wrote:
Lower them to arithmetic and bit manipulation expressions.
v2:
- Rewrite using ir_builder. [for idr]
- In lowering packHalf2x16, don't truncate subnormal float16 values
On 01/23/2013 06:06 AM, Ian Romanick wrote:
On 01/22/2013 10:36 PM, Matt Turner wrote:
On Mon, Jan 21, 2013 at 12:49 AM, Chad Versace
chad.vers...@linux.intel.com wrote:
+ /**
+* \brief Lower a packSnorm2x16 expression.
+*
+* \param vec2_rval is packSnorm2x16's input
+*
On 23 January 2013 12:44, Chad Versace chad.vers...@linux.intel.com wrote:
On 01/22/2013 09:19 PM, Paul Berry wrote:
On 21 January 2013 00:49, Chad Versace chad.vers...@linux.intel.com
wrote:
Lower them to arithmetic and bit manipulation expressions.
v2:
- Rewrite using
On 01/23/2013 03:48 PM, Chad Versace wrote:
On 01/23/2013 06:06 AM, Ian Romanick wrote:
On 01/22/2013 10:36 PM, Matt Turner wrote:
On Mon, Jan 21, 2013 at 12:49 AM, Chad Versace
chad.vers...@linux.intel.com wrote:
+ /**
+* \brief Lower a packSnorm2x16 expression.
+*
+* \param
On Mon, Jan 21, 2013 at 12:49 AM, Chad Versace
chad.vers...@linux.intel.com wrote:
Lower them to arithmetic and bit manipulation expressions.
v2:
- Rewrite using ir_builder. [for idr]
- In lowering packHalf2x16, don't truncate subnormal float16 values to zero.
And round to even
On 21 January 2013 00:49, Chad Versace chad.vers...@linux.intel.com wrote:
Lower them to arithmetic and bit manipulation expressions.
v2:
- Rewrite using ir_builder. [for idr]
- In lowering packHalf2x16, don't truncate subnormal float16 values to
zero.
And round to even rather than
Lower them to arithmetic and bit manipulation expressions.
v2:
- Rewrite using ir_builder. [for idr]
- In lowering packHalf2x16, don't truncate subnormal float16 values to zero.
And round to even rather than to zero. [for stereotype441]
CC: Ian Romanick i...@freedesktop.org
CC: Paul
10 matches
Mail list logo