[Mesa-dev] [PATCH] r600g: rework handling of the constants

[Vincent Lejeune]

>From Vadim Girlin patch
---
 src/gallium/drivers/r600/r600_llvm.c   | 19 ++++++++++--------
 src/gallium/drivers/r600/r600_shader.c | 35 +++++++++++++++++++++++++---------
 2 files changed, 37 insertions(+), 17 deletions(-)

diff --git a/src/gallium/drivers/r600/r600_llvm.c 
b/src/gallium/drivers/r600/r600_llvm.c
index 22f5f11..f5a51ae 100644
--- a/src/gallium/drivers/r600/r600_llvm.c
+++ b/src/gallium/drivers/r600/r600_llvm.c
@@ -26,14 +26,14 @@ static LLVMValueRef llvm_fetch_const(
        enum tgsi_opcode_type type,
        unsigned swizzle)
 {
-       LLVMValueRef args[2];
-       args[0] = lp_build_const_int32(bld_base->base.gallivm,
-                       radeon_llvm_reg_index_soa(reg->Register.Index, 
swizzle));
-       args[1] = lp_build_const_int32(bld_base->base.gallivm, 0);
-       LLVMValueRef cval = build_intrinsic(bld_base->base.gallivm->builder,
-               "llvm.AMDGPU.load.const", bld_base->base.elem_type,
-               args, 2, LLVMReadNoneAttribute);
-
+       LLVMValueRef offset[2] = {
+               
LLVMConstInt(LLVMInt64TypeInContext(bld_base->base.gallivm->context), 0, false),
+               lp_build_const_int32(bld_base->base.gallivm, 
reg->Register.Index)
+       };
+       LLVMValueRef const_ptr = 
LLVMGetFirstGlobal(bld_base->base.gallivm->module);
+       LLVMValueRef ptr = LLVMBuildGEP(bld_base->base.gallivm->builder, 
const_ptr, offset, 2, "");
+       LLVMValueRef cvecval = LLVMBuildLoad(bld_base->base.gallivm->builder, 
ptr, "");
+       LLVMValueRef cval = 
LLVMBuildExtractElement(bld_base->base.gallivm->builder, cvecval, 
lp_build_const_int32(bld_base->base.gallivm, swizzle), "");
        return bitcast(bld_base, type, cval);
 }
 
@@ -538,6 +538,9 @@ LLVMModuleRef r600_tgsi_llvm(
        bld_base->op_actions[TGSI_OPCODE_TXP].emit = llvm_emit_tex;
        bld_base->op_actions[TGSI_OPCODE_CMP].emit = emit_cndlt;
 
+       LLVMTypeRef type = 
LLVMArrayType(LLVMVectorType(bld_base->base.elem_type, 4), 1024);
+       LLVMAddGlobalInAddressSpace(bld_base->base.gallivm->module, type, 
"const", 2);
+
        lp_build_tgsi_llvm(bld_base, tokens);
 
        radeon_llvm_finalize_module(ctx);
diff --git a/src/gallium/drivers/r600/r600_shader.c 
b/src/gallium/drivers/r600/r600_shader.c
index f6873c3..1152c6f 100644
--- a/src/gallium/drivers/r600/r600_shader.c
+++ b/src/gallium/drivers/r600/r600_shader.c
@@ -299,15 +299,21 @@ static unsigned r600_src_from_byte_stream(unsigned char * 
bytes,
 static unsigned r600_alu_from_byte_stream(struct r600_shader_ctx *ctx,
                                unsigned char * bytes, unsigned bytes_read)
 {
-       unsigned src_idx;
+       unsigned src_idx, src_num;
        struct r600_bytecode_alu alu;
-       unsigned src_const_reg[3];
+       unsigned src_use_sel[3];
+       unsigned src_sel[3] = {};
        uint32_t word0, word1;
-
+       
+       src_num = bytes[bytes_read++];
+       
        memset(&alu, 0, sizeof(alu));
-       for(src_idx = 0; src_idx < 3; src_idx++) {
+       for(src_idx = 0; src_idx < src_num; src_idx++) {
                unsigned i;
-               src_const_reg[src_idx] = bytes[bytes_read++];
+               src_use_sel[src_idx] = bytes[bytes_read++];
+               for (i = 0; i < 4; i++) {
+                       src_sel[src_idx] |= bytes[bytes_read++] << (i * 8);
+               }
                for (i = 0; i < 4; i++) {
                        alu.src[src_idx].value |= bytes[bytes_read++] << (i * 
8);
                }
@@ -327,10 +333,21 @@ static unsigned r600_alu_from_byte_stream(struct 
r600_shader_ctx *ctx,
                break;
        }
 
-       for(src_idx = 0; src_idx < 3; src_idx++) {
-               if (src_const_reg[src_idx]) {
-                       alu.src[src_idx].kc_bank = src_const_reg[src_idx] - 1;
-                       alu.src[src_idx].sel += 512;
+       for(src_idx = 0; src_idx < src_num; src_idx++) {
+               if (src_use_sel[src_idx]) {
+                       unsigned sel = src_sel[src_idx];
+
+                       alu.src[src_idx].chan = sel & 3;
+                       sel >>= 2;
+
+                       if (sel>=512) { /* constant */
+                               sel -= 512;
+                               alu.src[src_idx].kc_bank = sel >> 12;
+                               alu.src[src_idx].sel = (sel & 4095) + 512;
+                       }
+                       else {
+                               alu.src[src_idx].sel = sel;
+                       }
                }
        }
 
-- 
1.8.0.2

_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/mesa-dev