[Mesa-dev] [PATCH 3/4] vc4: Add QIR/QPU support for the 8-bit vector instructions.

[Eric Anholt]

---
 src/gallium/drivers/vc4/vc4_program.c  | 20 ++++++++++++++++++++
 src/gallium/drivers/vc4/vc4_qir.c      |  5 +++++
 src/gallium/drivers/vc4/vc4_qir.h      | 10 ++++++++++
 src/gallium/drivers/vc4/vc4_qpu_emit.c |  5 +++++
 4 files changed, 40 insertions(+)

diff --git a/src/gallium/drivers/vc4/vc4_program.c b/src/gallium/drivers/vc4/vc4_program.c
index ab2f885..b04c8d3 100644
--- a/src/gallium/drivers/vc4/vc4_program.c
+++ b/src/gallium/drivers/vc4/vc4_program.c
@@ -1062,6 +1062,26 @@ ntq_emit_alu(struct vc4_compile *c, nir_alu_instr *instr)
                                 qir_SUB(c, qir_uniform_ui(c, 0), src[0]));
                 break;
 
+        case nir_op_isadd_4x8:
+                *dest = qir_V8ADDS(c, src[0], src[1]);
+                break;
+
+        case nir_op_issub_4x8:
+                *dest = qir_V8SUBS(c, src[0], src[1]);
+                break;
+
+        case nir_op_imin_4x8:
+                *dest = qir_V8MIN(c, src[0], src[1]);
+                break;
+
+        case nir_op_imax_4x8:
+                *dest = qir_V8MAX(c, src[0], src[1]);
+                break;
+
+        case nir_op_imul_unorm_4x8:
+                *dest = qir_V8MULD(c, src[0], src[1]);
+                break;
+
         default:
                 fprintf(stderr, "unknown NIR ALU inst: ");
                 nir_print_instr(&instr->instr, stderr);
diff --git a/src/gallium/drivers/vc4/vc4_qir.c b/src/gallium/drivers/vc4/vc4_qir.c
index 254140a..016d6e2 100644
--- a/src/gallium/drivers/vc4/vc4_qir.c
+++ b/src/gallium/drivers/vc4/vc4_qir.c
@@ -40,6 +40,11 @@ static const struct qir_op_info qir_op_info[] = {
         [QOP_FSUB] = { "fsub", 1, 2 },
         [QOP_FMUL] = { "fmul", 1, 2 },
         [QOP_MUL24] = { "mul24", 1, 2 },
+        [QOP_V8MULD] = {"v8muld", 1, 2 },
+        [QOP_V8MIN] = {"v8min", 1, 2 },
+        [QOP_V8MAX] = {"v8max", 1, 2 },
+        [QOP_V8ADDS] = {"v8adds", 1, 2 },
+        [QOP_V8SUBS] = {"v8subs", 1, 2 },
         [QOP_FMIN] = { "fmin", 1, 2 },
         [QOP_FMAX] = { "fmax", 1, 2 },
         [QOP_FMINABS] = { "fminabs", 1, 2 },
diff --git a/src/gallium/drivers/vc4/vc4_qir.h b/src/gallium/drivers/vc4/vc4_qir.h
index cade795..d032fab 100644
--- a/src/gallium/drivers/vc4/vc4_qir.h
+++ b/src/gallium/drivers/vc4/vc4_qir.h
@@ -66,6 +66,11 @@ enum qop {
         QOP_FADD,
         QOP_FSUB,
         QOP_FMUL,
+        QOP_V8MULD,
+        QOP_V8MIN,
+        QOP_V8MAX,
+        QOP_V8ADDS,
+        QOP_V8SUBS,
         QOP_MUL24,
         QOP_FMIN,
         QOP_FMAX,
@@ -538,6 +543,11 @@ QIR_ALU1(MOV)
 QIR_ALU2(FADD)
 QIR_ALU2(FSUB)
 QIR_ALU2(FMUL)
+QIR_ALU2(V8MULD)
+QIR_ALU2(V8MIN)
+QIR_ALU2(V8MAX)
+QIR_ALU2(V8ADDS)
+QIR_ALU2(V8SUBS)
 QIR_ALU2(MUL24)
 QIR_ALU1(SEL_X_0_ZS)
 QIR_ALU1(SEL_X_0_ZC)
diff --git a/src/gallium/drivers/vc4/vc4_qpu_emit.c b/src/gallium/drivers/vc4/vc4_qpu_emit.c
index f324056..97f9ee0 100644
--- a/src/gallium/drivers/vc4/vc4_qpu_emit.c
+++ b/src/gallium/drivers/vc4/vc4_qpu_emit.c
@@ -204,6 +204,11 @@ vc4_generate_code(struct vc4_context *vc4, struct vc4_compile *c)
                         A(NOT),
 
                         M(FMUL),
+                        M(V8MULD),
+                        M(V8MIN),
+                        M(V8MAX),
+                        M(V8ADDS),
+                        M(V8SUBS),
                         M(MUL24),
                 };
 
-- 
2.1.4