diff options
| author | Marek Olšák <marek.olsak@amd.com> | 2015-10-10 22:43:19 +0200 |
|---|---|---|
| committer | Marek Olšák <marek.olsak@amd.com> | 2015-10-17 21:40:04 +0200 |
| commit | 7c10af64258ca3a839d9fc1f14957ef556878b43 (patch) | |
| tree | d719cca2cc367d2355fa4501544e9351699f76db | |
| parent | f2cdb68c8bb905cd76edae383e1cbbe0ae2c69ea (diff) | |
radeonsi: don't use the AMDGPU intrinsic for CMP
No difference according to shader-db.
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
| -rw-r--r-- | src/gallium/drivers/radeon/radeon_setup_tgsi_llvm.c | 31 |
1 files changed, 22 insertions, 9 deletions
diff --git a/src/gallium/drivers/radeon/radeon_setup_tgsi_llvm.c b/src/gallium/drivers/radeon/radeon_setup_tgsi_llvm.c index c22ea7c2552..ac99e732c94 100644 --- a/src/gallium/drivers/radeon/radeon_setup_tgsi_llvm.c +++ b/src/gallium/drivers/radeon/radeon_setup_tgsi_llvm.c @@ -919,7 +919,21 @@ static void emit_ucmp( LLVMBuildSelect(builder, v, emit_data->args[1], emit_data->args[2], ""); } -static void emit_cmp( +static void emit_cmp(const struct lp_build_tgsi_action *action, + struct lp_build_tgsi_context *bld_base, + struct lp_build_emit_data *emit_data) +{ + LLVMBuilderRef builder = bld_base->base.gallivm->builder; + LLVMValueRef cond, *args = emit_data->args; + + cond = LLVMBuildFCmp(builder, LLVMRealOLT, args[0], + bld_base->base.zero, ""); + + emit_data->output[emit_data->chan] = + LLVMBuildSelect(builder, cond, args[1], args[2], ""); +} + +static void emit_set_cond( const struct lp_build_tgsi_action *action, struct lp_build_tgsi_context * bld_base, struct lp_build_emit_data * emit_data) @@ -1503,8 +1517,7 @@ void radeon_llvm_context_init(struct radeon_llvm_context * ctx) bld_base->op_actions[TGSI_OPCODE_CEIL].intr_name = "llvm.ceil.f32"; bld_base->op_actions[TGSI_OPCODE_CLAMP].emit = build_tgsi_intrinsic_nomem; bld_base->op_actions[TGSI_OPCODE_CLAMP].intr_name = "llvm.AMDIL.clamp."; - bld_base->op_actions[TGSI_OPCODE_CMP].emit = build_tgsi_intrinsic_nomem; - bld_base->op_actions[TGSI_OPCODE_CMP].intr_name = "llvm.AMDGPU.cndlt"; + bld_base->op_actions[TGSI_OPCODE_CMP].emit = emit_cmp; bld_base->op_actions[TGSI_OPCODE_CONT].emit = cont_emit; bld_base->op_actions[TGSI_OPCODE_COS].emit = build_tgsi_intrinsic_nomem; bld_base->op_actions[TGSI_OPCODE_COS].intr_name = "llvm.cos.f32"; @@ -1573,13 +1586,13 @@ void radeon_llvm_context_init(struct radeon_llvm_context * ctx) bld_base->op_actions[TGSI_OPCODE_ROUND].intr_name = "llvm.rint.f32"; bld_base->op_actions[TGSI_OPCODE_RSQ].intr_name = "llvm.AMDGPU.rsq.clamped.f32"; bld_base->op_actions[TGSI_OPCODE_RSQ].emit = build_tgsi_intrinsic_nomem; - bld_base->op_actions[TGSI_OPCODE_SGE].emit = emit_cmp; - bld_base->op_actions[TGSI_OPCODE_SEQ].emit = emit_cmp; + bld_base->op_actions[TGSI_OPCODE_SGE].emit = emit_set_cond; + bld_base->op_actions[TGSI_OPCODE_SEQ].emit = emit_set_cond; bld_base->op_actions[TGSI_OPCODE_SHL].emit = emit_shl; - bld_base->op_actions[TGSI_OPCODE_SLE].emit = emit_cmp; - bld_base->op_actions[TGSI_OPCODE_SLT].emit = emit_cmp; - bld_base->op_actions[TGSI_OPCODE_SNE].emit = emit_cmp; - bld_base->op_actions[TGSI_OPCODE_SGT].emit = emit_cmp; + bld_base->op_actions[TGSI_OPCODE_SLE].emit = emit_set_cond; + bld_base->op_actions[TGSI_OPCODE_SLT].emit = emit_set_cond; + bld_base->op_actions[TGSI_OPCODE_SNE].emit = emit_set_cond; + bld_base->op_actions[TGSI_OPCODE_SGT].emit = emit_set_cond; bld_base->op_actions[TGSI_OPCODE_SIN].emit = build_tgsi_intrinsic_nomem; bld_base->op_actions[TGSI_OPCODE_SIN].intr_name = "llvm.sin.f32"; bld_base->op_actions[TGSI_OPCODE_SQRT].emit = build_tgsi_intrinsic_nomem; |