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]>

8 files changed, 103 insertions, 1 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;
diff --git a/src/gallium/auxiliary/tgsi/tgsi_info.c b/src/gallium/auxiliary/tgsi/tgsi_info.c
index 7a5d18f59c5..0beef44454d 100644
--- a/src/gallium/auxiliary/tgsi/tgsi_info.c
+++ b/src/gallium/auxiliary/tgsi/tgsi_info.c
@@ -219,6 +219,8 @@ static const struct tgsi_opcode_info opcode_info[TGSI_OPCODE_LAST] =
    { 1, 3, 1, 0, 0, 0, OTHR, "TEX2", TGSI_OPCODE_TEX2 },
    { 1, 3, 1, 0, 0, 0, OTHR, "TXB2", TGSI_OPCODE_TXB2 },
    { 1, 3, 1, 0, 0, 0, OTHR, "TXL2", TGSI_OPCODE_TXL2 },
+   { 1, 2, 0, 0, 0, 0, COMP, "IMUL_HI", TGSI_OPCODE_IMUL_HI },
+   { 1, 2, 0, 0, 0, 0, COMP, "UMUL_HI", TGSI_OPCODE_UMUL_HI },
 };
 
 const struct tgsi_opcode_info *
@@ -297,6 +299,7 @@ tgsi_opcode_infer_type( uint opcode )
    case TGSI_OPCODE_USLT:
    case TGSI_OPCODE_USNE:
    case TGSI_OPCODE_SVIEWINFO:
+   case TGSI_OPCODE_UMUL_HI:
       return TGSI_TYPE_UNSIGNED;
    case TGSI_OPCODE_ARL:
    case TGSI_OPCODE_ARR:
@@ -317,6 +320,7 @@ tgsi_opcode_infer_type( uint opcode )
    case TGSI_OPCODE_UARL:
    case TGSI_OPCODE_IABS:
    case TGSI_OPCODE_ISSG:
+   case TGSI_OPCODE_IMUL_HI:
       return TGSI_TYPE_SIGNED;
    default:
       return TGSI_TYPE_FLOAT;
@@ -339,7 +343,9 @@ tgsi_opcode_infer_src_type( uint opcode )
    case TGSI_OPCODE_CASE:
    case TGSI_OPCODE_SAMPLE_I:
    case TGSI_OPCODE_SAMPLE_I_MS:
+   case TGSI_OPCODE_UMUL_HI:
       return TGSI_TYPE_UNSIGNED;
+   case TGSI_OPCODE_IMUL_HI:
    case TGSI_OPCODE_I2F:
       return TGSI_TYPE_SIGNED;
    case TGSI_OPCODE_ARL:
diff --git a/src/gallium/auxiliary/tgsi/tgsi_opcode_tmp.h b/src/gallium/auxiliary/tgsi/tgsi_opcode_tmp.h
index b8144a8916b..1ef78ddcc8f 100644
--- a/src/gallium/auxiliary/tgsi/tgsi_opcode_tmp.h
+++ b/src/gallium/auxiliary/tgsi/tgsi_opcode_tmp.h
@@ -204,6 +204,9 @@ OP12(SAMPLE_INFO)
 
 OP13(UCMP)
 
+OP12(IMUL_HI)
+OP12(UMUL_HI)
+
 #undef OP00
 #undef OP01
 #undef OP10
diff --git a/src/gallium/auxiliary/tgsi/tgsi_util.c b/src/gallium/auxiliary/tgsi/tgsi_util.c
index b3bc8f283a4..73a0667fd06 100644
--- a/src/gallium/auxiliary/tgsi/tgsi_util.c
+++ b/src/gallium/auxiliary/tgsi/tgsi_util.c
@@ -243,6 +243,8 @@ tgsi_util_get_inst_usage_mask(const struct tgsi_full_instruction *inst,
    case TGSI_OPCODE_USHR:
    case TGSI_OPCODE_USLT:
    case TGSI_OPCODE_USNE:
+   case TGSI_OPCODE_IMUL_HI:
+   case TGSI_OPCODE_UMUL_HI:
       /* Channel-wise operations */
       read_mask = write_mask;
       break;
diff --git a/src/gallium/docs/source/tgsi.rst b/src/gallium/docs/source/tgsi.rst
index 41f2798d704..f80c08d3175 100644
--- a/src/gallium/docs/source/tgsi.rst
+++ b/src/gallium/docs/source/tgsi.rst
@@ -1103,6 +1103,36 @@ Support for these opcodes indicated by PIPE_SHADER_CAP_INTEGERS (all of them?)
   dst.w = src0.w \times src1.w
 
 
+.. opcode:: IMUL_HI - Signed Integer Multiply High Bits
+
+   The high 32bits of the multiplication of 2 signed integers are returned.
+
+.. math::
+
+  dst.x = (src0.x \times src1.x) >> 32
+
+  dst.y = (src0.y \times src1.y) >> 32
+
+  dst.z = (src0.z \times src1.z) >> 32
+
+  dst.w = (src0.w \times src1.w) >> 32
+
+
+.. opcode:: UMUL_HI - Unsigned Integer Multiply High Bits
+
+   The high 32bits of the multiplication of 2 unsigned integers are returned.
+
+.. math::
+
+  dst.x = (src0.x \times src1.x) >> 32
+
+  dst.y = (src0.y \times src1.y) >> 32
+
+  dst.z = (src0.z \times src1.z) >> 32
+
+  dst.w = (src0.w \times src1.w) >> 32
+
+
 .. opcode:: IDIV - Signed Integer Division
 
    TBD: behavior for division by zero.
diff --git a/src/gallium/include/pipe/p_shader_tokens.h b/src/gallium/include/pipe/p_shader_tokens.h
index 1beec054c1b..801090204fa 100644
--- a/src/gallium/include/pipe/p_shader_tokens.h
+++ b/src/gallium/include/pipe/p_shader_tokens.h
@@ -450,7 +450,10 @@ struct tgsi_property_data {
 #define TGSI_OPCODE_TXB2                178
 #define TGSI_OPCODE_TXL2                179
 
-#define TGSI_OPCODE_LAST                180
+#define TGSI_OPCODE_IMUL_HI             180
+#define TGSI_OPCODE_UMUL_HI             181
+
+#define TGSI_OPCODE_LAST                182
 
 #define TGSI_SAT_NONE            0  /* do not saturate */
 #define TGSI_SAT_ZERO_ONE        1  /* clamp to [0,1] */
diff --git a/src/gallium/tests/graw/vertex-shader/vert-imul_hi.sh b/src/gallium/tests/graw/vertex-shader/vert-imul_hi.sh
new file mode 100644
index 00000000000..60e2d80dd7f
--- /dev/null
+++ b/src/gallium/tests/graw/vertex-shader/vert-imul_hi.sh
@@ -0,0 +1,13 @@
+VERT
+DCL IN[0]
+DCL IN[1]
+DCL OUT[0], POSITION
+DCL OUT[1], COLOR
+DCL TEMP[0]
+DCL TEMP[1]
+IMM[0] INT32 {-2147483648, 2, 0, -1}
+MOV OUT[0], IN[0]
+IMUL_HI TEMP[0], IMM[0].xzzx, IMM[0].yzzy
+UMUL TEMP[0], TEMP[0], IMM[0].wwww
+I2F OUT[1], TEMP[0]
+END
diff --git a/src/gallium/tests/graw/vertex-shader/vert-umul_hi.sh b/src/gallium/tests/graw/vertex-shader/vert-umul_hi.sh
new file mode 100644
index 00000000000..4aa79fe8647
--- /dev/null
+++ b/src/gallium/tests/graw/vertex-shader/vert-umul_hi.sh
@@ -0,0 +1,11 @@
+VERT
+DCL IN[0]
+DCL IN[1]
+DCL OUT[0], POSITION
+DCL OUT[1], COLOR
+DCL TEMP[0]
+IMM[0] INT32 {4, 1073741824, 0, 1}
+MOV OUT[0], IN[0]
+UMUL_HI TEMP[0], IMM[0].xzzx, IMM[0].yzzy
+I2F OUT[1], TEMP[0]
+END