Re: [Mesa-dev] [PATCH v6] swr: implement clipPlanes/clipVertex/clipDistance/cullDistance

2016-06-08 Thread Cherniak, Bruce 
Reviewed-by: Bruce Cherniak  

> On Jun 8, 2016, at 9:59 AM, Tim Rowley  wrote:
> 
> v2: only load the clip vertex once
> 
> v3: fix clip enable logic, add cullDistance
> 
> v4: remove duplicate fields in vs jit key, fix test of clip fixup needed
> 
> v5: fix clipdistance linkage for slot!=0,4
> 
> v6: support clip+cull; passes most piglit clip (failures understood)
> ---
> docs/GL3.txt   |  2 +-
> src/gallium/drivers/swr/swr_context.h  |  2 ++
> src/gallium/drivers/swr/swr_screen.cpp |  3 +-
> src/gallium/drivers/swr/swr_shader.cpp | 65 ++
> src/gallium/drivers/swr/swr_shader.h   |  1 +
> src/gallium/drivers/swr/swr_state.cpp  | 25 -
> 6 files changed, 95 insertions(+), 3 deletions(-)
> 
> diff --git a/docs/GL3.txt b/docs/GL3.txt
> index e8d401d..4ba0366 100644
> --- a/docs/GL3.txt
> +++ b/docs/GL3.txt
> @@ -211,7 +211,7 @@ GL 4.5, GLSL 4.50:
>   GL_ARB_ES3_1_compatibilityDONE (nvc0, radeonsi)
>   GL_ARB_clip_control   DONE (i965, nv50, 
> nvc0, r600, radeonsi, llvmpipe, softpipe, swr)
>   GL_ARB_conditional_render_invertedDONE (i965, nv50, 
> nvc0, r600, radeonsi, llvmpipe, softpipe, swr)
> -  GL_ARB_cull_distance  DONE (i965, nv50, 
> nvc0, llvmpipe, softpipe)
> +  GL_ARB_cull_distance  DONE (i965, nv50, 
> nvc0, llvmpipe, softpipe, swr)
>   GL_ARB_derivative_control DONE (i965, nv50, 
> nvc0, r600, radeonsi)
>   GL_ARB_direct_state_accessDONE (all drivers)
>   GL_ARB_get_texture_sub_image  DONE (all drivers)
> diff --git a/src/gallium/drivers/swr/swr_context.h 
> b/src/gallium/drivers/swr/swr_context.h
> index a7383bb..75ecae3 100644
> --- a/src/gallium/drivers/swr/swr_context.h
> +++ b/src/gallium/drivers/swr/swr_context.h
> @@ -89,6 +89,8 @@ struct swr_draw_context {
>swr_jit_texture texturesFS[PIPE_MAX_SHADER_SAMPLER_VIEWS];
>swr_jit_sampler samplersFS[PIPE_MAX_SAMPLERS];
> 
> +   float userClipPlanes[PIPE_MAX_CLIP_PLANES][4];
> +
>SWR_SURFACE_STATE renderTargets[SWR_NUM_ATTACHMENTS];
> };
> 
> diff --git a/src/gallium/drivers/swr/swr_screen.cpp 
> b/src/gallium/drivers/swr/swr_screen.cpp
> index ca39202..af82c93 100644
> --- a/src/gallium/drivers/swr/swr_screen.cpp
> +++ b/src/gallium/drivers/swr/swr_screen.cpp
> @@ -333,6 +333,8 @@ swr_get_param(struct pipe_screen *screen, enum pipe_cap 
> param)
>case PIPE_CAP_TEXTURE_FLOAT_LINEAR:
>case PIPE_CAP_TEXTURE_HALF_FLOAT_LINEAR:
>   return 1;
> +   case PIPE_CAP_CULL_DISTANCE:
> +  return 1;
>case PIPE_CAP_TGSI_TXQS:
>case PIPE_CAP_FORCE_PERSAMPLE_INTERP:
>case PIPE_CAP_SHAREABLE_SHADERS:
> @@ -358,7 +360,6 @@ swr_get_param(struct pipe_screen *screen, enum pipe_cap 
> param)
>case PIPE_CAP_PCI_DEVICE:
>case PIPE_CAP_PCI_FUNCTION:
>case PIPE_CAP_FRAMEBUFFER_NO_ATTACHMENT:
> -   case PIPE_CAP_CULL_DISTANCE:
>case PIPE_CAP_PRIMITIVE_RESTART_FOR_PATCHES:
>case PIPE_CAP_TGSI_VOTE:
>   return 0;
> diff --git a/src/gallium/drivers/swr/swr_shader.cpp 
> b/src/gallium/drivers/swr/swr_shader.cpp
> index f26467e..8af0700 100644
> --- a/src/gallium/drivers/swr/swr_shader.cpp
> +++ b/src/gallium/drivers/swr/swr_shader.cpp
> @@ -40,6 +40,9 @@
> #include "swr_state.h"
> #include "swr_screen.h"
> 
> +static unsigned
> +locate_linkage(ubyte name, ubyte index, struct tgsi_shader_info *info);
> +
> bool operator==(const swr_jit_fs_key , const swr_jit_fs_key )
> {
>return !memcmp(, , sizeof(lhs));
> @@ -119,6 +122,11 @@ swr_generate_vs_key(struct swr_jit_vs_key ,
> {
>memset(, 0, sizeof(key));
> 
> +   key.clip_plane_mask =
> +  swr_vs->info.base.clipdist_writemask ?
> +  swr_vs->info.base.clipdist_writemask & 
> ctx->rasterizer->clip_plane_enable :
> +  ctx->rasterizer->clip_plane_enable;
> +
>swr_generate_sampler_key(swr_vs->info, ctx, PIPE_SHADER_VERTEX, key);
> }
> 
> @@ -251,6 +259,63 @@ BuilderSWR::CompileVS(struct swr_context *ctx, 
> swr_jit_vs_key )
>   }
>}
> 
> +   if (ctx->rasterizer->clip_plane_enable ||
> +   swr_vs->info.base.culldist_writemask) {
> +  unsigned clip_mask = ctx->rasterizer->clip_plane_enable;
> +
> +  unsigned cv = 0;
> +  if (swr_vs->info.base.writes_clipvertex) {
> + cv = 1 + locate_linkage(TGSI_SEMANTIC_CLIPVERTEX, 0,
> + _vs->info.base);
> +  } else {
> + for (int i = 0; i < PIPE_MAX_SHADER_OUTPUTS; i++) {
> +if (swr_vs->info.base.output_semantic_name[i] == 
> TGSI_SEMANTIC_POSITION &&
> +swr_vs->info.base.output_semantic_index[i] == 0) {
> +   cv = i;
> +   break;
> +}
> + }
> +  }
> +  LLVMValueRef cx = LLVMBuildLoad(gallivm->builder, outputs[cv][0], "");

[Mesa-dev] [PATCH v6] swr: implement clipPlanes/clipVertex/clipDistance/cullDistance

2016-06-08 Thread Tim Rowley 
v2: only load the clip vertex once

v3: fix clip enable logic, add cullDistance

v4: remove duplicate fields in vs jit key, fix test of clip fixup needed

v5: fix clipdistance linkage for slot!=0,4

v6: support clip+cull; passes most piglit clip (failures understood)
---
 docs/GL3.txt   |  2 +-
 src/gallium/drivers/swr/swr_context.h  |  2 ++
 src/gallium/drivers/swr/swr_screen.cpp |  3 +-
 src/gallium/drivers/swr/swr_shader.cpp | 65 ++
 src/gallium/drivers/swr/swr_shader.h   |  1 +
 src/gallium/drivers/swr/swr_state.cpp  | 25 -
 6 files changed, 95 insertions(+), 3 deletions(-)

diff --git a/docs/GL3.txt b/docs/GL3.txt
index e8d401d..4ba0366 100644
--- a/docs/GL3.txt
+++ b/docs/GL3.txt
@@ -211,7 +211,7 @@ GL 4.5, GLSL 4.50:
   GL_ARB_ES3_1_compatibilityDONE (nvc0, radeonsi)
   GL_ARB_clip_control   DONE (i965, nv50, 
nvc0, r600, radeonsi, llvmpipe, softpipe, swr)
   GL_ARB_conditional_render_invertedDONE (i965, nv50, 
nvc0, r600, radeonsi, llvmpipe, softpipe, swr)
-  GL_ARB_cull_distance  DONE (i965, nv50, 
nvc0, llvmpipe, softpipe)
+  GL_ARB_cull_distance  DONE (i965, nv50, 
nvc0, llvmpipe, softpipe, swr)
   GL_ARB_derivative_control DONE (i965, nv50, 
nvc0, r600, radeonsi)
   GL_ARB_direct_state_accessDONE (all drivers)
   GL_ARB_get_texture_sub_image  DONE (all drivers)
diff --git a/src/gallium/drivers/swr/swr_context.h 
b/src/gallium/drivers/swr/swr_context.h
index a7383bb..75ecae3 100644
--- a/src/gallium/drivers/swr/swr_context.h
+++ b/src/gallium/drivers/swr/swr_context.h
@@ -89,6 +89,8 @@ struct swr_draw_context {
swr_jit_texture texturesFS[PIPE_MAX_SHADER_SAMPLER_VIEWS];
swr_jit_sampler samplersFS[PIPE_MAX_SAMPLERS];
 
+   float userClipPlanes[PIPE_MAX_CLIP_PLANES][4];
+
SWR_SURFACE_STATE renderTargets[SWR_NUM_ATTACHMENTS];
 };
 
diff --git a/src/gallium/drivers/swr/swr_screen.cpp 
b/src/gallium/drivers/swr/swr_screen.cpp
index ca39202..af82c93 100644
--- a/src/gallium/drivers/swr/swr_screen.cpp
+++ b/src/gallium/drivers/swr/swr_screen.cpp
@@ -333,6 +333,8 @@ swr_get_param(struct pipe_screen *screen, enum pipe_cap 
param)
case PIPE_CAP_TEXTURE_FLOAT_LINEAR:
case PIPE_CAP_TEXTURE_HALF_FLOAT_LINEAR:
   return 1;
+   case PIPE_CAP_CULL_DISTANCE:
+  return 1;
case PIPE_CAP_TGSI_TXQS:
case PIPE_CAP_FORCE_PERSAMPLE_INTERP:
case PIPE_CAP_SHAREABLE_SHADERS:
@@ -358,7 +360,6 @@ swr_get_param(struct pipe_screen *screen, enum pipe_cap 
param)
case PIPE_CAP_PCI_DEVICE:
case PIPE_CAP_PCI_FUNCTION:
case PIPE_CAP_FRAMEBUFFER_NO_ATTACHMENT:
-   case PIPE_CAP_CULL_DISTANCE:
case PIPE_CAP_PRIMITIVE_RESTART_FOR_PATCHES:
case PIPE_CAP_TGSI_VOTE:
   return 0;
diff --git a/src/gallium/drivers/swr/swr_shader.cpp 
b/src/gallium/drivers/swr/swr_shader.cpp
index f26467e..8af0700 100644
--- a/src/gallium/drivers/swr/swr_shader.cpp
+++ b/src/gallium/drivers/swr/swr_shader.cpp
@@ -40,6 +40,9 @@
 #include "swr_state.h"
 #include "swr_screen.h"
 
+static unsigned
+locate_linkage(ubyte name, ubyte index, struct tgsi_shader_info *info);
+
 bool operator==(const swr_jit_fs_key , const swr_jit_fs_key )
 {
return !memcmp(, , sizeof(lhs));
@@ -119,6 +122,11 @@ swr_generate_vs_key(struct swr_jit_vs_key ,
 {
memset(, 0, sizeof(key));
 
+   key.clip_plane_mask =
+  swr_vs->info.base.clipdist_writemask ?
+  swr_vs->info.base.clipdist_writemask & 
ctx->rasterizer->clip_plane_enable :
+  ctx->rasterizer->clip_plane_enable;
+
swr_generate_sampler_key(swr_vs->info, ctx, PIPE_SHADER_VERTEX, key);
 }
 
@@ -251,6 +259,63 @@ BuilderSWR::CompileVS(struct swr_context *ctx, 
swr_jit_vs_key )
   }
}
 
+   if (ctx->rasterizer->clip_plane_enable ||
+   swr_vs->info.base.culldist_writemask) {
+  unsigned clip_mask = ctx->rasterizer->clip_plane_enable;
+
+  unsigned cv = 0;
+  if (swr_vs->info.base.writes_clipvertex) {
+ cv = 1 + locate_linkage(TGSI_SEMANTIC_CLIPVERTEX, 0,
+ _vs->info.base);
+  } else {
+ for (int i = 0; i < PIPE_MAX_SHADER_OUTPUTS; i++) {
+if (swr_vs->info.base.output_semantic_name[i] == 
TGSI_SEMANTIC_POSITION &&
+swr_vs->info.base.output_semantic_index[i] == 0) {
+   cv = i;
+   break;
+}
+ }
+  }
+  LLVMValueRef cx = LLVMBuildLoad(gallivm->builder, outputs[cv][0], "");
+  LLVMValueRef cy = LLVMBuildLoad(gallivm->builder, outputs[cv][1], "");
+  LLVMValueRef cz = LLVMBuildLoad(gallivm->builder, outputs[cv][2], "");
+  LLVMValueRef cw = LLVMBuildLoad(gallivm->builder, outputs[cv][3], "");
+
+  for (unsigned val = 0; val < PIPE_MAX_CLIP_PLANES; val++) {
+ // clip distance overrides