gallium: Add support for 32x32 muls with 64 bit results

The code introduces two new 32bit integer multiplication opcodes which
can be used to produce correct 64 bit results. GLSL, OpenCL and D3D10+
require them. We use two seperate opcodes, because they match the
behavior of GLSL and OpenCL, are a lot easier to add than a single
opcode with multiple destinations and because there's not much (any)
difference wrt code-generation.

Signed-off-by: Zack Rusin <[email protected]>
Reviewed-by: José Fonseca <[email protected]>
Reviewed-by: Roland Scheidegger <[email protected]>
Reviewed-by: Brian Paul <[email protected]>

1 files changed, 34 insertions, 0 deletions

diff --git a/src/gallium/auxiliary/tgsi/tgsi_exec.c b/src/gallium/auxiliary/tgsi/tgsi_exec.c
index 0750a502f16..6db1238a60d 100644
--- a/src/gallium/auxiliary/tgsi/tgsi_exec.c
+++ b/src/gallium/auxiliary/tgsi/tgsi_exec.c
@@ -3478,6 +3478,32 @@ micro_umul(union tgsi_exec_channel *dst,
 }
 
 static void
+micro_imul_hi(union tgsi_exec_channel *dst,
+              const union tgsi_exec_channel *src0,
+              const union tgsi_exec_channel *src1)
+{
+#define I64M(x, y) ((((int64_t)x) * ((int64_t)y)) >> 32)
+   dst->i[0] = I64M(src0->i[0], src1->i[0]);
+   dst->i[1] = I64M(src0->i[1], src1->i[1]);
+   dst->i[2] = I64M(src0->i[2], src1->i[2]);
+   dst->i[3] = I64M(src0->i[3], src1->i[3]);
+#undef I64M
+}
+
+static void
+micro_umul_hi(union tgsi_exec_channel *dst,
+              const union tgsi_exec_channel *src0,
+              const union tgsi_exec_channel *src1)
+{
+#define U64M(x, y) ((((uint64_t)x) * ((uint64_t)y)) >> 32)
+   dst->u[0] = U64M(src0->u[0], src1->u[0]);
+   dst->u[1] = U64M(src0->u[1], src1->u[1]);
+   dst->u[2] = U64M(src0->u[2], src1->u[2]);
+   dst->u[3] = U64M(src0->u[3], src1->u[3]);
+#undef U64M
+}
+
+static void
 micro_useq(union tgsi_exec_channel *dst,
            const union tgsi_exec_channel *src0,
            const union tgsi_exec_channel *src1)
@@ -4277,6 +4303,14 @@ exec_instruction(
       exec_vector_binary(mach, inst, micro_umul, TGSI_EXEC_DATA_UINT, TGSI_EXEC_DATA_UINT);
       break;
 
+   case TGSI_OPCODE_IMUL_HI:
+      exec_vector_binary(mach, inst, micro_imul_hi, TGSI_EXEC_DATA_INT, TGSI_EXEC_DATA_INT);
+      break;
+
+   case TGSI_OPCODE_UMUL_HI:
+      exec_vector_binary(mach, inst, micro_umul_hi, TGSI_EXEC_DATA_UINT, TGSI_EXEC_DATA_UINT);
+      break;
+
    case TGSI_OPCODE_USEQ:
       exec_vector_binary(mach, inst, micro_useq, TGSI_EXEC_DATA_UINT, TGSI_EXEC_DATA_UINT);
       break;