r600g: fix F2I on evergreen

Signed-off-by: Vadim Girlin <[email protected]>

1 files changed, 50 insertions, 1 deletions

diff --git a/src/gallium/drivers/r600/r600_shader.c b/src/gallium/drivers/r600/r600_shader.c
index bc3652b477c..a3c1a4f12bb 100644
--- a/src/gallium/drivers/r600/r600_shader.c
+++ b/src/gallium/drivers/r600/r600_shader.c
@@ -1878,6 +1878,55 @@ static int tgsi_pow(struct r600_shader_ctx *ctx)
 	return tgsi_helper_tempx_replicate(ctx);
 }
 
+static int tgsi_f2i(struct r600_shader_ctx *ctx)
+{
+	struct tgsi_full_instruction *inst = &ctx->parse.FullToken.FullInstruction;
+	struct r600_bytecode_alu alu;
+	int i, r;
+	unsigned write_mask = inst->Dst[0].Register.WriteMask;
+	int last_inst = tgsi_last_instruction(write_mask);
+
+	for (i = 0; i < 4; i++) {
+		if (!(write_mask & (1<<i)))
+			continue;
+
+		memset(&alu, 0, sizeof(struct r600_bytecode_alu));
+		alu.inst = CTX_INST(V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_TRUNC);
+
+		alu.dst.sel = ctx->temp_reg;
+		alu.dst.chan = i;
+		alu.dst.write = 1;
+
+		r600_bytecode_src(&alu.src[0], &ctx->src[0], i);
+		if (i == last_inst)
+			alu.last = 1;
+		r = r600_bytecode_add_alu(ctx->bc, &alu);
+		if (r)
+			return r;
+	}
+
+	for (i = 0; i < 4; i++) {
+		if (!(write_mask & (1<<i)))
+			continue;
+
+		memset(&alu, 0, sizeof(struct r600_bytecode_alu));
+		alu.inst = CTX_INST(V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_FLT_TO_INT);
+
+		tgsi_dst(ctx, &inst->Dst[0], i, &alu.dst);
+
+		alu.src[0].sel = ctx->temp_reg;
+		alu.src[0].chan = i;
+
+		if (i == last_inst)
+			alu.last = 1;
+		r = r600_bytecode_add_alu(ctx->bc, &alu);
+		if (r)
+			return r;
+	}
+
+	return 0;
+}
+
 static int tgsi_ssg(struct r600_shader_ctx *ctx)
 {
 	struct tgsi_full_instruction *inst = &ctx->parse.FullToken.FullInstruction;
@@ -3798,7 +3847,7 @@ static struct r600_shader_tgsi_instruction eg_shader_tgsi_instruction[] = {
 	{TGSI_OPCODE_END,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_NOP, tgsi_end},  /* aka HALT */
 	/* gap */
 	{118,			0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_NOP, tgsi_unsupported},
-	{TGSI_OPCODE_F2I,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_FLT_TO_INT, tgsi_op2},
+	{TGSI_OPCODE_F2I,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_FLT_TO_INT, tgsi_f2i},
 	{TGSI_OPCODE_IDIV,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_NOP, tgsi_unsupported},
 	{TGSI_OPCODE_IMAX,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_MAX_INT, tgsi_op2},
 	{TGSI_OPCODE_IMIN,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_MIN_INT, tgsi_op2},