From: Marek Olšák <marek.ol...@amd.com>
---
src/amd/common/ac_llvm_build.h | 1 +
src/amd/common/ac_nir_to_llvm.c | 9 +++------
src/gallium/drivers/radeonsi/si_shader.c | 11 +++--------
3 files changed, 7 insertions(+), 14 deletions(-)
diff --git a/src/amd/common/ac_llvm_build.h b/src/amd/common/ac_llvm_build.h
index 5d39458..2d6efb5 100644
--- a/src/amd/common/ac_llvm_build.h
+++ b/src/amd/common/ac_llvm_build.h
@@ -28,20 +28,21 @@
#include <stdbool.h>
#include <llvm-c/TargetMachine.h>
#include "amd_family.h"
#ifdef __cplusplus
extern "C" {
#endif
enum {
+ AC_CONST_ADDR_SPACE = 2, /* CONST is the only address space that
selects SMEM loads */
AC_LOCAL_ADDR_SPACE = 3,
};
struct ac_llvm_context {
LLVMContextRef context;
LLVMModuleRef module;
LLVMBuilderRef builder;
LLVMTypeRef voidt;
LLVMTypeRef i1;
diff --git a/src/amd/common/ac_nir_to_llvm.c b/src/amd/common/ac_nir_to_llvm.c
index 187fdfb..0445d27 100644
--- a/src/amd/common/ac_nir_to_llvm.c
+++ b/src/amd/common/ac_nir_to_llvm.c
@@ -36,23 +36,20 @@
#include "ac_exp_param.h"
enum radeon_llvm_calling_convention {
RADEON_LLVM_AMDGPU_VS = 87,
RADEON_LLVM_AMDGPU_GS = 88,
RADEON_LLVM_AMDGPU_PS = 89,
RADEON_LLVM_AMDGPU_CS = 90,
RADEON_LLVM_AMDGPU_HS = 93,
};
-#define CONST_ADDR_SPACE 2
-#define LOCAL_ADDR_SPACE 3
-
#define RADEON_LLVM_MAX_INPUTS (VARYING_SLOT_VAR31 + 1)
#define RADEON_LLVM_MAX_OUTPUTS (VARYING_SLOT_VAR31 + 1)
struct nir_to_llvm_context;
struct ac_nir_context {
struct ac_llvm_context ac;
struct ac_shader_abi *abi;
gl_shader_stage stage;
@@ -350,21 +347,21 @@ create_llvm_function(LLVMContextRef ctx, LLVMModuleRef
module,
LLVMAddTargetDependentFunctionAttr(main_function,
"unsafe-fp-math",
"true");
}
return main_function;
}
static LLVMTypeRef const_array(LLVMTypeRef elem_type, int num_elements)
{
return LLVMPointerType(LLVMArrayType(elem_type, num_elements),
- CONST_ADDR_SPACE);
+ AC_CONST_ADDR_SPACE);
}
static int get_elem_bits(struct ac_llvm_context *ctx, LLVMTypeRef type)
{
if (LLVMGetTypeKind(type) == LLVMVectorTypeKind)
type = LLVMGetElementType(type);
if (LLVMGetTypeKind(type) == LLVMIntegerTypeKind)
return LLVMGetIntTypeWidth(type);
@@ -1036,21 +1033,21 @@ static void create_function(struct nir_to_llvm_context
*ctx,
assign_arguments(ctx->main_function, &args);
user_sgpr_idx = 0;
if (ctx->options->supports_spill || user_sgpr_info.need_ring_offsets) {
set_loc_shader(ctx, AC_UD_SCRATCH_RING_OFFSETS,
&user_sgpr_idx, 2);
if (ctx->options->supports_spill) {
ctx->ring_offsets = ac_build_intrinsic(&ctx->ac,
"llvm.amdgcn.implicit.buffer.ptr",
-
LLVMPointerType(ctx->ac.i8, CONST_ADDR_SPACE),
+
LLVMPointerType(ctx->ac.i8, AC_CONST_ADDR_SPACE),
NULL, 0,
AC_FUNC_ATTR_READNONE);
ctx->ring_offsets = LLVMBuildBitCast(ctx->builder,
ctx->ring_offsets,
const_array(ctx->ac.v4i32, 16), "");
}
}
/* For merged shaders the user SGPRs start at 8, with 8 system SGPRs in
front (including
* the rw_buffers at s0/s1. With user SGPR0 = s8, lets restart the
count from 0 */
if (has_previous_stage)
user_sgpr_idx = 0;
@@ -5564,21 +5561,21 @@ setup_locals(struct ac_nir_context *ctx,
static void
setup_shared(struct ac_nir_context *ctx,
struct nir_shader *nir)
{
nir_foreach_variable(variable, &nir->shared) {
LLVMValueRef shared =
LLVMAddGlobalInAddressSpace(
ctx->ac.module, glsl_to_llvm_type(ctx->nctx,
variable->type),
variable->name ? variable->name : "",
- LOCAL_ADDR_SPACE);
+ AC_LOCAL_ADDR_SPACE);
_mesa_hash_table_insert(ctx->vars, variable, shared);
}
}
static LLVMValueRef
emit_float_saturate(struct ac_llvm_context *ctx, LLVMValueRef v, float lo,
float hi)
{
v = ac_to_float(ctx, v);
v = emit_intrin_2f_param(ctx, "llvm.maxnum", ctx->f32, v,
LLVMConstReal(ctx->f32, lo));
return emit_intrin_2f_param(ctx, "llvm.minnum", ctx->f32, v,
LLVMConstReal(ctx->f32, hi));
diff --git a/src/gallium/drivers/radeonsi/si_shader.c
b/src/gallium/drivers/radeonsi/si_shader.c
index 708da13..a1cc6e1 100644
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -92,25 +92,20 @@ static void si_build_tcs_epilog_function(struct
si_shader_context *ctx,
static void si_build_ps_prolog_function(struct si_shader_context *ctx,
union si_shader_part_key *key);
static void si_build_ps_epilog_function(struct si_shader_context *ctx,
union si_shader_part_key *key);
/* Ideally pass the sample mask input to the PS epilog as v14, which
* is its usual location, so that the shader doesn't have to add v_mov.
*/
#define PS_EPILOG_SAMPLEMASK_MIN_LOC 14
-enum {
- CONST_ADDR_SPACE = 2,
- LOCAL_ADDR_SPACE = 3,
-};
-
static bool llvm_type_is_64bit(struct si_shader_context *ctx,
LLVMTypeRef type)
{
if (type == ctx->ac.i64 || type == ctx->ac.f64)
return true;
return false;
}
static bool is_merged_shader(struct si_shader *shader)
@@ -2173,31 +2168,31 @@ void si_load_system_value(struct si_shader_context *ctx,
}
ctx->system_values[index] = value;
}
void si_declare_compute_memory(struct si_shader_context *ctx,
const struct tgsi_full_declaration *decl)
{
struct si_shader_selector *sel = ctx->shader->selector;
- LLVMTypeRef i8p = LLVMPointerType(ctx->i8, LOCAL_ADDR_SPACE);
+ LLVMTypeRef i8p = LLVMPointerType(ctx->i8, AC_LOCAL_ADDR_SPACE);
LLVMValueRef var;
assert(decl->Declaration.MemType == TGSI_MEMORY_TYPE_SHARED);
assert(decl->Range.First == decl->Range.Last);
assert(!ctx->ac.lds);
var = LLVMAddGlobalInAddressSpace(ctx->ac.module,
LLVMArrayType(ctx->i8,
sel->local_size),
"compute_lds",
- LOCAL_ADDR_SPACE);
+ AC_LOCAL_ADDR_SPACE);
LLVMSetAlignment(var, 4);
ctx->ac.lds = LLVMBuildBitCast(ctx->ac.builder, var, i8p, "");
}
static LLVMValueRef load_const_buffer_desc(struct si_shader_context *ctx, int
i)
{
LLVMValueRef list_ptr = LLVMGetParam(ctx->main_fn,
ctx->param_const_and_shader_buffers);
@@ -3828,21 +3823,21 @@ static void clock_emit(
emit_data->output[0] =
LLVMBuildExtractElement(ctx->ac.builder, tmp, ctx->i32_0, "");
emit_data->output[1] =
LLVMBuildExtractElement(ctx->ac.builder, tmp, ctx->i32_1, "");
}
LLVMTypeRef si_const_array(LLVMTypeRef elem_type, int num_elements)
{
return LLVMPointerType(LLVMArrayType(elem_type, num_elements),
- CONST_ADDR_SPACE);
+ AC_CONST_ADDR_SPACE);
}
static void si_llvm_emit_ddxy(
const struct lp_build_tgsi_action *action,
struct lp_build_tgsi_context *bld_base,
struct lp_build_emit_data *emit_data)
{
struct si_shader_context *ctx = si_shader_context(bld_base);
unsigned opcode = emit_data->info->opcode;
LLVMValueRef val;
--
2.7.4
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
