[Mesa-dev] [PATCH 1/3] r600g/llvm: rework handling of the constants

[Vincent Lejeune]

From: Vadim Girlin <vadimgirlin at gmail.com>

Pack kc_bank, const_index and chan into the load.const operand, unpack
them in r600_alu_from_byte_stream and use to override sel, kc_bank and chan
for the constants.

Expected operand value is (((512 + (kc_bank << 12) + const_index) << 2) + chan).
---
 src/gallium/drivers/r600/r600_llvm.c   |  6 +++++-
 src/gallium/drivers/r600/r600_shader.c | 33 ++++++++++++++++++++++++++-------
 2 files changed, 31 insertions(+), 8 deletions(-)

diff --git a/src/gallium/drivers/r600/r600_llvm.c b/src/gallium/drivers/r600/r600_llvm.c
index 17d362c..110ba64 100644
--- a/src/gallium/drivers/r600/r600_llvm.c
+++ b/src/gallium/drivers/r600/r600_llvm.c
@@ -25,8 +25,12 @@ static LLVMValueRef llvm_fetch_const(
 	enum tgsi_opcode_type type,
 	unsigned swizzle)
 {
+	/* load.const's operand currently goes through the compiler unmodified,
+	 * encoding expected by the bytestream reader is
+	 * ((512 + (4096 * kc_bank) + const_index)*4 + chan)
+	 */
 	LLVMValueRef idx = lp_build_const_int32(bld_base->base.gallivm,
-			radeon_llvm_reg_index_soa(reg->Register.Index, swizzle));
+			radeon_llvm_reg_index_soa(reg->Register.Index + 512, swizzle));
 	LLVMValueRef cval = build_intrinsic(bld_base->base.gallivm->builder,
 		"llvm.AMDGPU.load.const", bld_base->base.elem_type,
 		&idx, 1, LLVMReadNoneAttribute);
diff --git a/src/gallium/drivers/r600/r600_shader.c b/src/gallium/drivers/r600/r600_shader.c
index bca62ad..6056831 100644
--- a/src/gallium/drivers/r600/r600_shader.c
+++ b/src/gallium/drivers/r600/r600_shader.c
@@ -308,15 +308,21 @@ 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);
 		}
@@ -336,9 +342,22 @@ 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].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;
+			}
+		}
 	}
 
 #if HAVE_LLVM < 0x0302
-- 
1.8.0.1