+<dl>
+<dt><code>INTEL_NO_HW</code></dt>
+<dd>if set to 1, prevents batches from being submitted to the hardware.
+ This is useful for debugging hangs, etc.</dd>
+<dt><code>INTEL_DEBUG</code></dt>
+<dd>a comma-separated list of named flags, which do various things:
+<dl>
+ <dt><code>ann</code></dt>
+ <dd>annotate IR in assembly dumps</dd>
+ <dt><code>aub</code></dt>
+ <dd>dump batches into an AUB trace for use with simulation tools</dd>
+ <dt><code>bat</code></dt>
+ <dd>emit batch information</dd>
+ <dt><code>blit</code></dt>
+ <dd>emit messages about blit operations</dd>
+ <dt><code>blorp</code></dt>
+ <dd>emit messages about the blorp operations (blits & clears)</dd>
+ <dt><code>buf</code></dt>
+ <dd>emit messages about buffer objects</dd>
+ <dt><code>clip</code></dt>
+ <dd>emit messages about the clip unit (for old gens, includes the CLIP program)</dd>
+ <dt><code>color</code></dt>
+ <dd>use color in output</dd>
+ <dt><code>cs</code></dt>
+ <dd>dump shader assembly for compute shaders</dd>
+ <dt><code>do32</code></dt>
+ <dd>generate compute shader SIMD32 programs even if workgroup size doesn't exceed the SIMD16 limit</dd>
+ <dt><code>dri</code></dt>
+ <dd>emit messages about the DRI interface</dd>
+ <dt><code>fbo</code></dt>
+ <dd>emit messages about framebuffers</dd>
+ <dt><code>fs</code></dt>
+ <dd>dump shader assembly for fragment shaders</dd>
+ <dt><code>gs</code></dt>
+ <dd>dump shader assembly for geometry shaders</dd>
+ <dt><code>hex</code></dt>
+ <dd>print instruction hex dump with the disassembly</dd>
+ <dt><code>l3</code></dt>
+ <dd>emit messages about the new L3 state during transitions</dd>
+ <dt><code>miptree</code></dt>
+ <dd>emit messages about miptrees</dd>
+ <dt><code>no8</code></dt>
+ <dd>don't generate SIMD8 fragment shader</dd>
+ <dt><code>no16</code></dt>
+ <dd>suppress generation of 16-wide fragment shaders. useful for debugging broken shaders</dd>
+ <dt><code>nocompact</code></dt>
+ <dd>disable instruction compaction</dd>
+ <dt><code>nodualobj</code></dt>
+ <dd>suppress generation of dual-object geometry shader code</dd>
+ <dt><code>norbc</code></dt>
+ <dd>disable single sampled render buffer compression</dd>
+ <dt><code>optimizer</code></dt>
+ <dd>dump shader assembly to files at each optimization pass and iteration that make progress</dd>
+ <dt><code>perf</code></dt>
+ <dd>emit messages about performance issues</dd>
+ <dt><code>perfmon</code></dt>
+ <dd>emit messages about <code>AMD_performance_monitor</code></dd>
+ <dt><code>pix</code></dt>
+ <dd>emit messages about pixel operations</dd>
+ <dt><code>prim</code></dt>
+ <dd>emit messages about drawing primitives</dd>
+ <dt><code>reemit</code></dt>
+ <dd>mark all state dirty on each draw call</dd>
+ <dt><code>sf</code></dt>
+ <dd>emit messages about the strips & fans unit (for old gens, includes the SF program)</dd>
+ <dt><code>shader_time</code></dt>
+ <dd>record how much GPU time is spent in each shader</dd>
+ <dt><code>spill_fs</code></dt>
+ <dd>force spilling of all registers in the scalar backend (useful to debug spilling code)</dd>
+ <dt><code>spill_vec4</code></dt>
+ <dd>force spilling of all registers in the vec4 backend (useful to debug spilling code)</dd>
+ <dt><code>state</code></dt>
+ <dd>emit messages about state flag tracking</dd>
+ <dt><code>submit</code></dt>
+ <dd>emit batchbuffer usage statistics</dd>
+ <dt><code>sync</code></dt>
+ <dd>after sending each batch, emit a message and wait for that batch to finish rendering</dd>
+ <dt><code>tcs</code></dt>
+ <dd>dump shader assembly for tessellation control shaders</dd>
+ <dt><code>tes</code></dt>
+ <dd>dump shader assembly for tessellation evaluation shaders</dd>
+ <dt><code>tex</code></dt>
+ <dd>emit messages about textures.</dd>
+ <dt><code>urb</code></dt>
+ <dd>emit messages about URB setup</dd>
+ <dt><code>vert</code></dt>
+ <dd>emit messages about vertex assembly</dd>
+ <dt><code>vs</code></dt>
+ <dd>dump shader assembly for vertex shaders</dd>
+</dl>
+</dd>
+<dt><code>INTEL_SCALAR_VS</code> (or <code>TCS</code>, <code>TES</code>,
+ <code>GS</code>)</dt>
+<dd>force scalar/vec4 mode for a shader stage (Gen8-9 only)</dd>
+<dt><code>INTEL_PRECISE_TRIG</code></dt>
+<dd>if set to 1, true or yes, then the driver prefers accuracy over
+ performance in trig functions.</dd>
+</dl>