[Mesa-dev] [PATCH 3/4] radeonsi: add fine derivate control
Dave Airlie
airlied at gmail.com
Tue Jul 21 15:51:36 PDT 2015
From: Dave Airlie <airlied at redhat.com>
This adds support for fine derivatives and enables
ARB_derivative_control on radeonsi.
(just fell out of my working out interpolation)
Signed-off-by: Dave Airlie <airlied at redhat.com>
---
docs/GL3.txt | 2 +-
docs/relnotes/10.7.0.html | 1 +
src/gallium/drivers/radeonsi/si_pipe.c | 5 +++--
src/gallium/drivers/radeonsi/si_shader.c | 20 ++++++++++++++++----
4 files changed, 21 insertions(+), 7 deletions(-)
diff --git a/docs/GL3.txt b/docs/GL3.txt
index 33a282e..4f6c415 100644
--- a/docs/GL3.txt
+++ b/docs/GL3.txt
@@ -191,7 +191,7 @@ GL 4.5, GLSL 4.50:
GL_ARB_clip_control DONE (i965, nv50, nvc0, r600, radeonsi, llvmpipe, softpipe)
GL_ARB_conditional_render_inverted DONE (i965, nv50, nvc0, llvmpipe, softpipe)
GL_ARB_cull_distance in progress (Tobias)
- GL_ARB_derivative_control DONE (i965, nv50, nvc0, r600)
+ GL_ARB_derivative_control DONE (i965, nv50, nvc0, r600, radeonsi)
GL_ARB_direct_state_access DONE (all drivers)
- Transform Feedback object DONE
- Buffer object DONE
diff --git a/docs/relnotes/10.7.0.html b/docs/relnotes/10.7.0.html
index 42ea807..a69971f 100644
--- a/docs/relnotes/10.7.0.html
+++ b/docs/relnotes/10.7.0.html
@@ -45,6 +45,7 @@ Note: some of the new features are only available with certain drivers.
<ul>
<li>GL_AMD_vertex_shader_viewport_index on radeonsi</li>
+<li>GL_ARB_derivative_control on radeonsi</li>
<li>GL_ARB_fragment_layer_viewport on radeonsi</li>
<li>GL_ARB_framebuffer_no_attachments on i965</li>
<li>GL_ARB_gpu_shader_fp64 on llvmpipe, radeonsi</li>
diff --git a/src/gallium/drivers/radeonsi/si_pipe.c b/src/gallium/drivers/radeonsi/si_pipe.c
index 2b6a6ff..f725677 100644
--- a/src/gallium/drivers/radeonsi/si_pipe.c
+++ b/src/gallium/drivers/radeonsi/si_pipe.c
@@ -284,7 +284,8 @@ static int si_get_param(struct pipe_screen* pscreen, enum pipe_cap param)
return HAVE_LLVM >= 0x0305;
case PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS:
return HAVE_LLVM >= 0x0305 ? 4 : 0;
-
+ case PIPE_CAP_TGSI_FS_FINE_DERIVATIVE:
+ return 1;
/* Unsupported features. */
case PIPE_CAP_TGSI_FS_COORD_ORIGIN_LOWER_LEFT:
case PIPE_CAP_TGSI_CAN_COMPACT_CONSTANTS:
@@ -293,7 +294,7 @@ static int si_get_param(struct pipe_screen* pscreen, enum pipe_cap param)
case PIPE_CAP_USER_VERTEX_BUFFERS:
case PIPE_CAP_FAKE_SW_MSAA:
case PIPE_CAP_TEXTURE_GATHER_OFFSETS:
- case PIPE_CAP_TGSI_FS_FINE_DERIVATIVE:
+
case PIPE_CAP_CONDITIONAL_RENDER_INVERTED:
case PIPE_CAP_SAMPLER_VIEW_TARGET:
case PIPE_CAP_VERTEXID_NOBASE:
diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
index f23eaa4..c5d80f0 100644
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -2203,7 +2203,8 @@ static void si_llvm_emit_ddxy(
LLVMTypeRef i32;
unsigned swizzle[4];
unsigned c;
-
+ int idx;
+ unsigned mask;
i32 = LLVMInt32TypeInContext(gallivm->context);
indices[0] = bld_base->uint_bld.zero;
@@ -2212,14 +2213,21 @@ static void si_llvm_emit_ddxy(
store_ptr = LLVMBuildGEP(gallivm->builder, si_shader_ctx->ddxy_lds,
indices, 2, "");
+ if (opcode == TGSI_OPCODE_DDX_FINE)
+ mask = 0xfffffffe;
+ else if (opcode == TGSI_OPCODE_DDY_FINE)
+ mask = 0xfffffffd;
+ else
+ mask = 0xfffffffc;
indices[1] = LLVMBuildAnd(gallivm->builder, indices[1],
- lp_build_const_int32(gallivm, 0xfffffffc), "");
+ lp_build_const_int32(gallivm, mask), "");
load_ptr0 = LLVMBuildGEP(gallivm->builder, si_shader_ctx->ddxy_lds,
indices, 2, "");
+ idx = (opcode == TGSI_OPCODE_DDX || opcode == TGSI_OPCODE_DDX_FINE) ? 1 :2;
indices[1] = LLVMBuildAdd(gallivm->builder, indices[1],
lp_build_const_int32(gallivm,
- opcode == TGSI_OPCODE_DDX ? 1 : 2),
+ idx),
"");
load_ptr1 = LLVMBuildGEP(gallivm->builder, si_shader_ctx->ddxy_lds,
indices, 2, "");
@@ -2506,7 +2514,9 @@ static void create_function(struct si_shader_context *si_shader_ctx)
if (bld_base->info &&
(bld_base->info->opcode_count[TGSI_OPCODE_DDX] > 0 ||
- bld_base->info->opcode_count[TGSI_OPCODE_DDY] > 0))
+ bld_base->info->opcode_count[TGSI_OPCODE_DDY] > 0 ||
+ bld_base->info->opcode_count[TGSI_OPCODE_DDX_FINE] > 0 ||
+ bld_base->info->opcode_count[TGSI_OPCODE_DDY_FINE] > 0))
si_shader_ctx->ddxy_lds =
LLVMAddGlobalInAddressSpace(gallivm->module,
LLVMArrayType(i32, 64),
@@ -2959,6 +2969,8 @@ int si_shader_create(struct si_screen *sscreen, LLVMTargetMachineRef tm,
bld_base->op_actions[TGSI_OPCODE_DDX].emit = si_llvm_emit_ddxy;
bld_base->op_actions[TGSI_OPCODE_DDY].emit = si_llvm_emit_ddxy;
+ bld_base->op_actions[TGSI_OPCODE_DDX_FINE].emit = si_llvm_emit_ddxy;
+ bld_base->op_actions[TGSI_OPCODE_DDY_FINE].emit = si_llvm_emit_ddxy;
bld_base->op_actions[TGSI_OPCODE_EMIT].emit = si_llvm_emit_vertex;
bld_base->op_actions[TGSI_OPCODE_ENDPRIM].emit = si_llvm_emit_primitive;
--
2.4.3
More information about the mesa-dev
mailing list