i965/fs/generator: add new opcode to set float controls modes in control register

Before this commit, we had only FPRoundingMode decoration (the per
instruction one) that is applied during the SPIR-V handling. In
vtn_alu we find out the rounding mode, and generate the code
accordingly that later will be used to look for the respective
nir_op_f2f16_{rtz,rtne}.

Per-instruction gets prioritized because we make them explicit
conversions (with RTZ or RTNE nir opcodes) and they will override the
default execution mode defined with float controls. However, we need
to come back to the mode defined by float controls after the execution
of the FP Rounding instruction.

Therefore, the new SHADER_OPCODE_FLOAT_CONTROL_MODE opcode will be
used to set the default rounding mode and denorms treatment in the
whole shader while the pre-existent SHADER_OPCODE_RND_MODE, will be
used as prioritized rounding mode in a per-instruction basis.

v2:
- Fix bug in defining BRW_CR0_FP_MODE_MASK.

v3:
- Update comment (Caio).

v4:
- Split the patch into the helper and the new opcode (this
  one) (Caio).

v5:
- Add an explanation on the actual purpose and priority of the newly
  introduced opcode in the commit log (Caio).

Signed-off-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>

diff --git a/src/intel/compiler/brw_eu_defines.h b/src/intel/compiler/brw_eu_defines.h
index 1d4c0b8..7024f01 100644 (file)
--- a/src/intel/compiler/brw_eu_defines.h
+++ b/src/intel/compiler/brw_eu_defines.h
@@ -441,6 +441,7 @@ enum opcode {
    SHADER_OPCODE_TYPED_SURFACE_WRITE_LOGICAL,
 
    SHADER_OPCODE_RND_MODE,
+   SHADER_OPCODE_FLOAT_CONTROL_MODE,
 
    /**
     * Byte scattered write/read opcodes.
@@ -1383,6 +1384,15 @@ enum PACKED brw_rnd_mode {
    BRW_RND_MODE_UNSPECIFIED,  /* Unspecified rounding mode */
 };
 
+#define BRW_CR0_FP64_DENORM_PRESERVE (1 << 6)
+#define BRW_CR0_FP32_DENORM_PRESERVE (1 << 7)
+#define BRW_CR0_FP16_DENORM_PRESERVE (1 << 10)
+
+#define BRW_CR0_FP_MODE_MASK (BRW_CR0_FP64_DENORM_PRESERVE | \
+                              BRW_CR0_FP32_DENORM_PRESERVE | \
+                              BRW_CR0_FP16_DENORM_PRESERVE | \
+                              BRW_CR0_RND_MODE_MASK)
+
 /* MDC_DS - Data Size Message Descriptor Control Field
  * Skylake PRM, Volume 2d, page 129
  *

diff --git a/src/intel/compiler/brw_fs_generator.cpp b/src/intel/compiler/brw_fs_generator.cpp
index 48ac635..a946255 100644 (file)
--- a/src/intel/compiler/brw_fs_generator.cpp
+++ b/src/intel/compiler/brw_fs_generator.cpp
@@ -2230,6 +2230,12 @@ fs_generator::generate_code(const cfg_t *cfg, int dispatch_width,
       }
          break;
 
+      case SHADER_OPCODE_FLOAT_CONTROL_MODE:
+         assert(src[0].file == BRW_IMMEDIATE_VALUE);
+         assert(src[1].file == BRW_IMMEDIATE_VALUE);
+         brw_float_controls_mode(p, src[0].d, src[1].d);
+         break;
+
       default:
          unreachable("Unsupported opcode");
 

diff --git a/src/intel/compiler/brw_shader.cpp b/src/intel/compiler/brw_shader.cpp
index 1a414cf..d1672d3 100644 (file)
--- a/src/intel/compiler/brw_shader.cpp
+++ b/src/intel/compiler/brw_shader.cpp
@@ -519,6 +519,8 @@ brw_instruction_name(const struct gen_device_info *devinfo, enum opcode op)
 
    case SHADER_OPCODE_RND_MODE:
       return "rnd_mode";
+   case SHADER_OPCODE_FLOAT_CONTROL_MODE:
+      return "float_control_mode";
    }
 
    unreachable("not reached");
@@ -1067,6 +1069,7 @@ backend_instruction::has_side_effects() const
    case TCS_OPCODE_URB_WRITE:
    case TCS_OPCODE_RELEASE_INPUT:
    case SHADER_OPCODE_RND_MODE:
+   case SHADER_OPCODE_FLOAT_CONTROL_MODE:
       return true;
    default:
       return eot;