radeonsi: enable TGSI support cap for compute shaders
v2: Use chip_class instead of family. v3: Check kernel version for SI. v4: Preemptively allow amdgpu winsys for SI. Signed-off-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Marek Olšák <marek.olsak@amd.com>
This commit is contained in:
@@ -167,7 +167,7 @@ GL 4.3, GLSL 4.30:
|
|||||||
GL_ARB_arrays_of_arrays DONE (all drivers that support GLSL 1.30)
|
GL_ARB_arrays_of_arrays DONE (all drivers that support GLSL 1.30)
|
||||||
GL_ARB_ES3_compatibility DONE (all drivers that support GLSL 3.30)
|
GL_ARB_ES3_compatibility DONE (all drivers that support GLSL 3.30)
|
||||||
GL_ARB_clear_buffer_object DONE (all drivers)
|
GL_ARB_clear_buffer_object DONE (all drivers)
|
||||||
GL_ARB_compute_shader DONE (i965)
|
GL_ARB_compute_shader DONE (i965, radeonsi)
|
||||||
GL_ARB_copy_image DONE (i965, nv50, nvc0, r600, radeonsi)
|
GL_ARB_copy_image DONE (i965, nv50, nvc0, r600, radeonsi)
|
||||||
GL_KHR_debug DONE (all drivers)
|
GL_KHR_debug DONE (all drivers)
|
||||||
GL_ARB_explicit_uniform_location DONE (all drivers that support GLSL)
|
GL_ARB_explicit_uniform_location DONE (all drivers that support GLSL)
|
||||||
@@ -225,7 +225,7 @@ GL 4.5, GLSL 4.50:
|
|||||||
These are the extensions cherry-picked to make GLES 3.1
|
These are the extensions cherry-picked to make GLES 3.1
|
||||||
GLES3.1, GLSL ES 3.1
|
GLES3.1, GLSL ES 3.1
|
||||||
GL_ARB_arrays_of_arrays DONE (all drivers that support GLSL 1.30)
|
GL_ARB_arrays_of_arrays DONE (all drivers that support GLSL 1.30)
|
||||||
GL_ARB_compute_shader DONE (i965)
|
GL_ARB_compute_shader DONE (i965, radeonsi)
|
||||||
GL_ARB_draw_indirect DONE (i965, nvc0, r600, radeonsi, llvmpipe, softpipe)
|
GL_ARB_draw_indirect DONE (i965, nvc0, r600, radeonsi, llvmpipe, softpipe)
|
||||||
GL_ARB_explicit_uniform_location DONE (all drivers that support GLSL)
|
GL_ARB_explicit_uniform_location DONE (all drivers that support GLSL)
|
||||||
GL_ARB_framebuffer_no_attachments DONE (i965, nvc0, r600, radeonsi, softpipe)
|
GL_ARB_framebuffer_no_attachments DONE (i965, nvc0, r600, radeonsi, softpipe)
|
||||||
|
@@ -45,6 +45,7 @@ Note: some of the new features are only available with certain drivers.
|
|||||||
|
|
||||||
<ul>
|
<ul>
|
||||||
<li>OpenGL 4.2 on radeonsi</li>
|
<li>OpenGL 4.2 on radeonsi</li>
|
||||||
|
<li>GL_ARB_compute_shader on radeonsi</li>
|
||||||
<li>GL_ARB_framebuffer_no_attachments on nvc0, r600, radeonsi, softpipe</li>
|
<li>GL_ARB_framebuffer_no_attachments on nvc0, r600, radeonsi, softpipe</li>
|
||||||
<li>GL_ARB_internalformat_query2 on all drivers</li>
|
<li>GL_ARB_internalformat_query2 on all drivers</li>
|
||||||
<li>GL_ARB_robust_buffer_access_behavior on radeonsi</li>
|
<li>GL_ARB_robust_buffer_access_behavior on radeonsi</li>
|
||||||
|
@@ -646,23 +646,34 @@ static int r600_get_compute_param(struct pipe_screen *screen,
|
|||||||
uint64_t *grid_size = ret;
|
uint64_t *grid_size = ret;
|
||||||
grid_size[0] = 65535;
|
grid_size[0] = 65535;
|
||||||
grid_size[1] = 65535;
|
grid_size[1] = 65535;
|
||||||
grid_size[2] = 1;
|
grid_size[2] = 65535;
|
||||||
}
|
}
|
||||||
return 3 * sizeof(uint64_t) ;
|
return 3 * sizeof(uint64_t) ;
|
||||||
|
|
||||||
case PIPE_COMPUTE_CAP_MAX_BLOCK_SIZE:
|
case PIPE_COMPUTE_CAP_MAX_BLOCK_SIZE:
|
||||||
if (ret) {
|
if (ret) {
|
||||||
uint64_t *block_size = ret;
|
uint64_t *block_size = ret;
|
||||||
block_size[0] = 256;
|
if (rscreen->chip_class >= SI && HAVE_LLVM >= 0x309 &&
|
||||||
block_size[1] = 256;
|
ir_type == PIPE_SHADER_IR_TGSI) {
|
||||||
block_size[2] = 256;
|
block_size[0] = 2048;
|
||||||
|
block_size[1] = 2048;
|
||||||
|
block_size[2] = 2048;
|
||||||
|
} else {
|
||||||
|
block_size[0] = 256;
|
||||||
|
block_size[1] = 256;
|
||||||
|
block_size[2] = 256;
|
||||||
|
}
|
||||||
}
|
}
|
||||||
return 3 * sizeof(uint64_t);
|
return 3 * sizeof(uint64_t);
|
||||||
|
|
||||||
case PIPE_COMPUTE_CAP_MAX_THREADS_PER_BLOCK:
|
case PIPE_COMPUTE_CAP_MAX_THREADS_PER_BLOCK:
|
||||||
if (ret) {
|
if (ret) {
|
||||||
uint64_t *max_threads_per_block = ret;
|
uint64_t *max_threads_per_block = ret;
|
||||||
*max_threads_per_block = 256;
|
if (rscreen->chip_class >= SI && HAVE_LLVM >= 0x309 &&
|
||||||
|
ir_type == PIPE_SHADER_IR_TGSI)
|
||||||
|
*max_threads_per_block = 2048;
|
||||||
|
else
|
||||||
|
*max_threads_per_block = 256;
|
||||||
}
|
}
|
||||||
return sizeof(uint64_t);
|
return sizeof(uint64_t);
|
||||||
|
|
||||||
|
@@ -473,6 +473,8 @@ static int si_get_param(struct pipe_screen* pscreen, enum pipe_cap param)
|
|||||||
|
|
||||||
static int si_get_shader_param(struct pipe_screen* pscreen, unsigned shader, enum pipe_shader_cap param)
|
static int si_get_shader_param(struct pipe_screen* pscreen, unsigned shader, enum pipe_shader_cap param)
|
||||||
{
|
{
|
||||||
|
struct si_screen *sscreen = (struct si_screen *)pscreen;
|
||||||
|
|
||||||
switch(shader)
|
switch(shader)
|
||||||
{
|
{
|
||||||
case PIPE_SHADER_FRAGMENT:
|
case PIPE_SHADER_FRAGMENT:
|
||||||
@@ -490,9 +492,19 @@ static int si_get_shader_param(struct pipe_screen* pscreen, unsigned shader, enu
|
|||||||
case PIPE_SHADER_CAP_PREFERRED_IR:
|
case PIPE_SHADER_CAP_PREFERRED_IR:
|
||||||
return PIPE_SHADER_IR_NATIVE;
|
return PIPE_SHADER_IR_NATIVE;
|
||||||
|
|
||||||
case PIPE_SHADER_CAP_SUPPORTED_IRS:
|
case PIPE_SHADER_CAP_SUPPORTED_IRS: {
|
||||||
return 0;
|
int ir = 1 << PIPE_SHADER_IR_NATIVE;
|
||||||
|
|
||||||
|
/* Old kernels disallowed some register writes for SI
|
||||||
|
* that are used for indirect dispatches. */
|
||||||
|
if (HAVE_LLVM >= 0x309 && (sscreen->b.chip_class >= CIK ||
|
||||||
|
sscreen->b.info.drm_major == 3 ||
|
||||||
|
(sscreen->b.info.drm_major == 2 &&
|
||||||
|
sscreen->b.info.drm_minor >= 45)))
|
||||||
|
ir |= 1 << PIPE_SHADER_IR_TGSI;
|
||||||
|
|
||||||
|
return ir;
|
||||||
|
}
|
||||||
case PIPE_SHADER_CAP_DOUBLES:
|
case PIPE_SHADER_CAP_DOUBLES:
|
||||||
return HAVE_LLVM >= 0x0307;
|
return HAVE_LLVM >= 0x0307;
|
||||||
|
|
||||||
|
Reference in New Issue
Block a user