From a4ff1fd388369dbf80d324c84502b28b5f9d3da4 Mon Sep 17 00:00:00 2001 From: Kenneth Graunke Date: Wed, 14 Aug 2013 18:55:15 -0700 Subject: [PATCH] i965: Shorten sampler loops in precompile key setup. Now that we have the number of samplers available, we don't need to iterate over all 16. This should be particularly helpful for vertex shaders. v2: Use the correct shader program (caught by Paul Berry). This needs to initialize the exact same set of sampler swizzles as the actual key setup, or else we end up doing recompiles due to some being XYZW and others being 0. Signed-off-by: Kenneth Graunke Reviewed-by: Paul Berry --- src/mesa/drivers/dri/i965/brw_fs.cpp | 3 ++- src/mesa/drivers/dri/i965/brw_vs.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp index d111cbd28cd..52fa6f4a750 100644 --- a/src/mesa/drivers/dri/i965/brw_fs.cpp +++ b/src/mesa/drivers/dri/i965/brw_fs.cpp @@ -3157,7 +3157,8 @@ brw_fs_precompile(struct gl_context *ctx, struct gl_shader_program *prog) key.clamp_fragment_color = ctx->API == API_OPENGL_COMPAT; - for (int i = 0; i < MAX_SAMPLERS; i++) { + unsigned sampler_count = _mesa_fls(fp->Base.SamplersUsed); + for (unsigned i = 0; i < sampler_count; i++) { if (fp->Base.ShadowSamplers & (1 << i)) { /* Assume DEPTH_TEXTURE_MODE is the default: X, X, X, 1 */ key.tex.swizzles[i] = diff --git a/src/mesa/drivers/dri/i965/brw_vs.c b/src/mesa/drivers/dri/i965/brw_vs.c index dcd14a319df..ee77b019740 100644 --- a/src/mesa/drivers/dri/i965/brw_vs.c +++ b/src/mesa/drivers/dri/i965/brw_vs.c @@ -530,7 +530,8 @@ brw_vs_precompile(struct gl_context *ctx, struct gl_shader_program *prog) key.base.program_string_id = bvp->id; key.base.clamp_vertex_color = ctx->API == API_OPENGL_COMPAT; - for (int i = 0; i < MAX_SAMPLERS; i++) { + unsigned sampler_count = _mesa_fls(vp->Base.SamplersUsed); + for (unsigned i = 0; i < sampler_count; i++) { if (vp->Base.ShadowSamplers & (1 << i)) { /* Assume DEPTH_TEXTURE_MODE is the default: X, X, X, 1 */ key.base.tex.swizzles[i] = -- 2.30.2