r600g: add support for ISHR/USHR/SHL on r600-evergreen

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

2 files changed, 13 insertions, 10 deletions

diff --git a/src/gallium/drivers/r600/r600_asm.c b/src/gallium/drivers/r600/r600_asm.c
index 3b281c60e39..23350e25967 100644
--- a/src/gallium/drivers/r600/r600_asm.c
+++ b/src/gallium/drivers/r600/r600_asm.c
@@ -86,6 +86,9 @@ static inline unsigned int r600_bytecode_get_num_operands(struct r600_bytecode *
 		case V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_DOT4_IEEE:
 		case V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_CUBE:
 		case V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_XOR_INT:
+		case V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_LSHL_INT:
+		case V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_LSHR_INT:
+		case V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_ASHR_INT:
 			return 2;
 
 		case V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_MOV:
@@ -161,6 +164,9 @@ static inline unsigned int r600_bytecode_get_num_operands(struct r600_bytecode *
 		case EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INTERP_XY:
 		case EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INTERP_ZW:
 		case EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_XOR_INT:
+		case EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_LSHL_INT:
+		case EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_LSHR_INT:
+		case EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_ASHR_INT:
 			return 2;
 
 		case EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_MOV:
@@ -505,10 +511,7 @@ static int is_alu_trans_unit_inst(struct r600_bytecode *bc, struct r600_bytecode
 			/* Note that FLT_TO_INT_* instructions are vector-only instructions
 			 * on Evergreen, despite what the documentation says. FLT_TO_INT
 			 * can do both vector and scalar. */
-			return alu->inst == EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_ASHR_INT ||
-			        alu->inst == EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_INT_TO_FLT ||
-				alu->inst == EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_LSHL_INT ||
-				alu->inst == EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_LSHR_INT ||
+			return alu->inst == EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_INT_TO_FLT ||
 				alu->inst == EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_MULHI_INT ||
 				alu->inst == EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_MULHI_UINT ||
 				alu->inst == EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_MULLO_INT ||
diff --git a/src/gallium/drivers/r600/r600_shader.c b/src/gallium/drivers/r600/r600_shader.c
index e92e361fb79..0942aa10ec0 100644
--- a/src/gallium/drivers/r600/r600_shader.c
+++ b/src/gallium/drivers/r600/r600_shader.c
@@ -3976,7 +3976,7 @@ static struct r600_shader_tgsi_instruction r600_shader_tgsi_instruction[] = {
 	{TGSI_OPCODE_I2F,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_INT_TO_FLT, tgsi_op2_trans},
 	{TGSI_OPCODE_NOT,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_NOT_INT, tgsi_op2},
 	{TGSI_OPCODE_TRUNC,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_TRUNC, tgsi_op2},
-	{TGSI_OPCODE_SHL,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_NOP, tgsi_unsupported},
+	{TGSI_OPCODE_SHL,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_LSHL_INT, tgsi_op2_trans},
 	/* gap */
 	{88,			0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_NOP, tgsi_unsupported},
 	{TGSI_OPCODE_AND,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_AND_INT, tgsi_op2},
@@ -4018,7 +4018,7 @@ static struct r600_shader_tgsi_instruction r600_shader_tgsi_instruction[] = {
 	{TGSI_OPCODE_IMIN,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_MIN_INT, tgsi_op2},
 	{TGSI_OPCODE_INEG,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_SUB_INT, tgsi_op2},
 	{TGSI_OPCODE_ISGE,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_SETGE_INT, tgsi_op2},
-	{TGSI_OPCODE_ISHR,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_NOP, tgsi_unsupported},
+	{TGSI_OPCODE_ISHR,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_ASHR_INT, tgsi_op2_trans},
 	{TGSI_OPCODE_ISLT,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_SETGT_INT, tgsi_op2},
 	{TGSI_OPCODE_F2U,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_FLT_TO_UINT, tgsi_op2},
 	{TGSI_OPCODE_U2F,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_UINT_TO_FLT, tgsi_op2_trans},
@@ -4031,7 +4031,7 @@ static struct r600_shader_tgsi_instruction r600_shader_tgsi_instruction[] = {
 	{TGSI_OPCODE_UMUL,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_MULLO_UINT, tgsi_op2},
 	{TGSI_OPCODE_USEQ,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_SETE_INT, tgsi_op2},
 	{TGSI_OPCODE_USGE,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_SETGE_UINT, tgsi_op2},
-	{TGSI_OPCODE_USHR,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_NOP, tgsi_unsupported},
+	{TGSI_OPCODE_USHR,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_LSHR_INT, tgsi_op2_trans},
 	{TGSI_OPCODE_USLT,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_SETGT_INT, tgsi_op2_swap},
 	{TGSI_OPCODE_USNE,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_SETNE_INT, tgsi_op2_swap},
 	{TGSI_OPCODE_SWITCH,	0, V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_NOP, tgsi_unsupported},
@@ -4150,7 +4150,7 @@ static struct r600_shader_tgsi_instruction eg_shader_tgsi_instruction[] = {
 	{TGSI_OPCODE_I2F,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_INT_TO_FLT, tgsi_op2_trans},
 	{TGSI_OPCODE_NOT,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_NOT_INT, tgsi_op2},
 	{TGSI_OPCODE_TRUNC,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_TRUNC, tgsi_op2},
-	{TGSI_OPCODE_SHL,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_NOP, tgsi_unsupported},
+	{TGSI_OPCODE_SHL,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_LSHL_INT, tgsi_op2},
 	/* gap */
 	{88,			0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_NOP, tgsi_unsupported},
 	{TGSI_OPCODE_AND,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_AND_INT, tgsi_op2},
@@ -4192,7 +4192,7 @@ static struct r600_shader_tgsi_instruction eg_shader_tgsi_instruction[] = {
 	{TGSI_OPCODE_IMIN,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_MIN_INT, tgsi_op2},
 	{TGSI_OPCODE_INEG,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_SUB_INT, tgsi_ineg},
 	{TGSI_OPCODE_ISGE,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_SETGE_INT, tgsi_op2},
-	{TGSI_OPCODE_ISHR,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_NOP, tgsi_unsupported},
+	{TGSI_OPCODE_ISHR,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_ASHR_INT, tgsi_op2},
 	{TGSI_OPCODE_ISLT,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_SETGT_INT, tgsi_op2_swap},
 	{TGSI_OPCODE_F2U,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_FLT_TO_UINT, tgsi_f2i},
 	{TGSI_OPCODE_U2F,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_UINT_TO_FLT, tgsi_op2},
@@ -4205,7 +4205,7 @@ static struct r600_shader_tgsi_instruction eg_shader_tgsi_instruction[] = {
 	{TGSI_OPCODE_UMUL,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_MULLO_UINT, tgsi_op2_trans},
 	{TGSI_OPCODE_USEQ,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_SETE_INT, tgsi_op2},
 	{TGSI_OPCODE_USGE,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_SETGE_UINT, tgsi_op2},
-	{TGSI_OPCODE_USHR,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_NOP, tgsi_unsupported},
+	{TGSI_OPCODE_USHR,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_LSHR_INT, tgsi_op2},
 	{TGSI_OPCODE_USLT,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_SETGT_INT, tgsi_op2_swap},
 	{TGSI_OPCODE_USNE,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_SETNE_INT, tgsi_op2},
 	{TGSI_OPCODE_SWITCH,	0, EG_V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_NOP, tgsi_unsupported},