[Mesa-dev] [PATCH 5/8] radeonsi: implement SAMPLEPOS fragment shader input
Marek Olšák
maraeo at gmail.com
Wed May 7 09:45:31 PDT 2014
It's a pseudo-code that would be inserted at the beginning of the
shader by the shader compiler. gl_SamplePos is always read-only from a
user's point of view.
Marek
On Wed, May 7, 2014 at 6:02 PM, Ilia Mirkin <imirkin at alum.mit.edu> wrote:
> On Wed, May 7, 2014 at 11:56 AM, Marek Olšák <maraeo at gmail.com> wrote:
>> I could enable interpolation of gl_FragCoord at the sample instead of
>> centroid and do:
>>
>> gl_SamplePos = fract(gl_FragCoord.xy);
>
> Is that legal? I didn't think that sample position could be an output,
> at least not with ARB_sample_shading (and not even with
> ARB_gpu_shader5). Perhaps some other extension adds it.
>
>> gl_FragCoord.xy = floor(gl_FragCoord.xy) + vec2(0.5); // center
>>
>> However, I wouldn't be able to get gl_FragCoord at the centroid.
>>
>> I'm also not sure how gl_FragCoord should be interpolated if sample
>> shading is enabled.
>>
>> Marek
>>
>> On Wed, May 7, 2014 at 5:00 PM, Ilia Mirkin <imirkin at alum.mit.edu> wrote:
>>> On Wed, May 7, 2014 at 10:00 AM, Marek Olšák <maraeo at gmail.com> wrote:
>>>> From: Marek Olšák <marek.olsak at amd.com>
>>>>
>>>> The sample positions are read from a constant buffer.
>>>
>>> FWIW I had to do the same thing in both nv50 and nvc0. I had proposed
>>> that this should actually be done directly by the state tracker, but I
>>> think claims were made to the effect that there might be hw which can
>>> look up the positions directly. I figured radeon was such hw, but I
>>> guess not.
>>>
>>> Anyways, seems like a nice refactor would be to have mesa/st (or
>>> mesa/main) supply the constbufs and rip out the extra logic from
>>> nv50/nvc0/radeonsi. [Certainly don't have to do it now, esp now that
>>> you've done it this way.] The sample count is already handled this way
>>> by mesa core.
>>>
>>> -ilia
>>>
>>>> ---
>>>> src/gallium/drivers/radeon/cayman_msaa.c | 17 +++++++++++++++++
>>>> src/gallium/drivers/radeon/r600_pipe_common.c | 1 +
>>>> src/gallium/drivers/radeon/r600_pipe_common.h | 10 ++++++++++
>>>> src/gallium/drivers/radeonsi/si_shader.c | 23 +++++++++++++++++++++++
>>>> src/gallium/drivers/radeonsi/si_state.c | 25 +++++++++++++++++++++++++
>>>> 5 files changed, 76 insertions(+)
>>>>
>>>> diff --git a/src/gallium/drivers/radeon/cayman_msaa.c b/src/gallium/drivers/radeon/cayman_msaa.c
>>>> index 8727f3e..47fc5c4 100644
>>>> --- a/src/gallium/drivers/radeon/cayman_msaa.c
>>>> +++ b/src/gallium/drivers/radeon/cayman_msaa.c
>>>> @@ -123,6 +123,23 @@ void cayman_get_sample_position(struct pipe_context *ctx, unsigned sample_count,
>>>> }
>>>> }
>>>>
>>>> +void cayman_init_msaa(struct pipe_context *ctx)
>>>> +{
>>>> + struct r600_common_context *rctx = (struct r600_common_context*)ctx;
>>>> + int i;
>>>> +
>>>> + cayman_get_sample_position(ctx, 1, 0, rctx->sample_locations_1x[0]);
>>>> +
>>>> + for (i = 0; i < 2; i++)
>>>> + cayman_get_sample_position(ctx, 2, i, rctx->sample_locations_2x[i]);
>>>> + for (i = 0; i < 4; i++)
>>>> + cayman_get_sample_position(ctx, 4, i, rctx->sample_locations_4x[i]);
>>>> + for (i = 0; i < 8; i++)
>>>> + cayman_get_sample_position(ctx, 8, i, rctx->sample_locations_8x[i]);
>>>> + for (i = 0; i < 16; i++)
>>>> + cayman_get_sample_position(ctx, 16, i, rctx->sample_locations_16x[i]);
>>>> +}
>>>> +
>>>> void cayman_emit_msaa_sample_locs(struct radeon_winsys_cs *cs, int nr_samples)
>>>> {
>>>> switch (nr_samples) {
>>>> diff --git a/src/gallium/drivers/radeon/r600_pipe_common.c b/src/gallium/drivers/radeon/r600_pipe_common.c
>>>> index 70c4d1a..4c6cf0e 100644
>>>> --- a/src/gallium/drivers/radeon/r600_pipe_common.c
>>>> +++ b/src/gallium/drivers/radeon/r600_pipe_common.c
>>>> @@ -154,6 +154,7 @@ bool r600_common_context_init(struct r600_common_context *rctx,
>>>> r600_init_context_texture_functions(rctx);
>>>> r600_streamout_init(rctx);
>>>> r600_query_init(rctx);
>>>> + cayman_init_msaa(&rctx->b);
>>>>
>>>> rctx->allocator_so_filled_size = u_suballocator_create(&rctx->b, 4096, 4,
>>>> 0, PIPE_USAGE_DEFAULT, TRUE);
>>>> diff --git a/src/gallium/drivers/radeon/r600_pipe_common.h b/src/gallium/drivers/radeon/r600_pipe_common.h
>>>> index 4c3e9ce..8862d31 100644
>>>> --- a/src/gallium/drivers/radeon/r600_pipe_common.h
>>>> +++ b/src/gallium/drivers/radeon/r600_pipe_common.h
>>>> @@ -357,6 +357,15 @@ struct r600_common_context {
>>>> boolean saved_render_cond_cond;
>>>> unsigned saved_render_cond_mode;
>>>>
>>>> + /* MSAA sample locations.
>>>> + * The first index is the sample index.
>>>> + * The second index is the coordinate: X, Y. */
>>>> + float sample_locations_1x[1][2];
>>>> + float sample_locations_2x[2][2];
>>>> + float sample_locations_4x[4][2];
>>>> + float sample_locations_8x[8][2];
>>>> + float sample_locations_16x[16][2];
>>>> +
>>>> /* Copy one resource to another using async DMA. */
>>>> void (*dma_copy)(struct pipe_context *ctx,
>>>> struct pipe_resource *dst,
>>>> @@ -472,6 +481,7 @@ extern const uint32_t eg_sample_locs_4x[4];
>>>> extern const unsigned eg_max_dist_4x;
>>>> void cayman_get_sample_position(struct pipe_context *ctx, unsigned sample_count,
>>>> unsigned sample_index, float *out_value);
>>>> +void cayman_init_msaa(struct pipe_context *ctx);
>>>> void cayman_emit_msaa_sample_locs(struct radeon_winsys_cs *cs, int nr_samples);
>>>> void cayman_emit_msaa_config(struct radeon_winsys_cs *cs, int nr_samples,
>>>> int ps_iter_samples);
>>>> diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
>>>> index 0195e54..d8b7b9c 100644
>>>> --- a/src/gallium/drivers/radeonsi/si_shader.c
>>>> +++ b/src/gallium/drivers/radeonsi/si_shader.c
>>>> @@ -559,6 +559,8 @@ static void declare_system_value(
>>>> {
>>>> struct si_shader_context *si_shader_ctx =
>>>> si_shader_context(&radeon_bld->soa.bld_base);
>>>> + struct lp_build_context *uint_bld = &radeon_bld->soa.bld_base.uint_bld;
>>>> + struct gallivm_state *gallivm = &radeon_bld->gallivm;
>>>> LLVMValueRef value = 0;
>>>>
>>>> switch (decl->Semantic.Name) {
>>>> @@ -576,6 +578,27 @@ static void declare_system_value(
>>>> value = get_sample_id(radeon_bld);
>>>> break;
>>>>
>>>> + case TGSI_SEMANTIC_SAMPLEPOS:
>>>> + {
>>>> + LLVMBuilderRef builder = gallivm->builder;
>>>> + LLVMValueRef desc = LLVMGetParam(si_shader_ctx->radeon_bld.main_fn, SI_PARAM_CONST);
>>>> + LLVMValueRef buf_index = lp_build_const_int32(gallivm, NUM_PIPE_CONST_BUFFERS);
>>>> + LLVMValueRef resource = build_indexed_load(si_shader_ctx, desc, buf_index);
>>>> +
>>>> + /* offset = sample_id * 8 (8 = 2 floats containing samplepos.xy) */
>>>> + LLVMValueRef offset0 = lp_build_mul_imm(uint_bld, get_sample_id(radeon_bld), 8);
>>>> + LLVMValueRef offset1 = LLVMBuildAdd(builder, offset0, lp_build_const_int32(gallivm, 4), "");
>>>> +
>>>> + LLVMValueRef pos[4] = {
>>>> + load_const(builder, resource, offset0, radeon_bld->soa.bld_base.base.elem_type),
>>>> + load_const(builder, resource, offset1, radeon_bld->soa.bld_base.base.elem_type),
>>>> + lp_build_const_float(gallivm, 0),
>>>> + lp_build_const_float(gallivm, 0)
>>>> + };
>>>> + value = lp_build_gather_values(gallivm, pos, 4);
>>>> + break;
>>>> + }
>>>> +
>>>> default:
>>>> assert(!"unknown system value");
>>>> return;
>>>> diff --git a/src/gallium/drivers/radeonsi/si_state.c b/src/gallium/drivers/radeonsi/si_state.c
>>>> index fd9de05..3c1af06 100644
>>>> --- a/src/gallium/drivers/radeonsi/si_state.c
>>>> +++ b/src/gallium/drivers/radeonsi/si_state.c
>>>> @@ -1859,6 +1859,7 @@ static void si_set_framebuffer_state(struct pipe_context *ctx,
>>>> const struct pipe_framebuffer_state *state)
>>>> {
>>>> struct si_context *sctx = (struct si_context *)ctx;
>>>> + struct pipe_constant_buffer constbuf = {0};
>>>> struct r600_surface *surf = NULL;
>>>> struct r600_texture *rtex;
>>>> int i;
>>>> @@ -1924,6 +1925,30 @@ static void si_set_framebuffer_state(struct pipe_context *ctx,
>>>> sctx->framebuffer.atom.num_dw += 18; /* MSAA sample locations */
>>>> sctx->framebuffer.atom.dirty = true;
>>>> sctx->msaa_config.dirty = true;
>>>> +
>>>> + /* Set sample locations as fragment shader constants. */
>>>> + switch (sctx->framebuffer.nr_samples) {
>>>> + case 1:
>>>> + constbuf.user_buffer = sctx->b.sample_locations_1x;
>>>> + break;
>>>> + case 2:
>>>> + constbuf.user_buffer = sctx->b.sample_locations_2x;
>>>> + break;
>>>> + case 4:
>>>> + constbuf.user_buffer = sctx->b.sample_locations_4x;
>>>> + break;
>>>> + case 8:
>>>> + constbuf.user_buffer = sctx->b.sample_locations_8x;
>>>> + break;
>>>> + case 16:
>>>> + constbuf.user_buffer = sctx->b.sample_locations_16x;
>>>> + break;
>>>> + default:
>>>> + assert(0);
>>>> + }
>>>> + constbuf.buffer_size = sctx->framebuffer.nr_samples * 2 * 4;
>>>> + ctx->set_constant_buffer(ctx, PIPE_SHADER_FRAGMENT,
>>>> + NUM_PIPE_CONST_BUFFERS, &constbuf);
>>>> }
>>>>
>>>> static void si_emit_framebuffer_state(struct si_context *sctx, struct r600_atom *atom)
>>>> --
>>>> 1.9.1
>>>>
>>>> _______________________________________________
>>>> mesa-dev mailing list
>>>> mesa-dev at lists.freedesktop.org
>>>> http://lists.freedesktop.org/mailman/listinfo/mesa-dev
More information about the mesa-dev
mailing list