[Libclc-dev] [PATCH 1/4] r600: Convert get_local_size to clc

Jan Vesely via Libclc-dev libclc-dev at lists.llvm.org
Sun Oct 28 23:40:26 PDT 2018


Signed-off-by: Jan Vesely <jan.vesely at rutgers.edu>
---
This series consolidates existing llvm asm variants to clc file.
I've verified that the code generated using llvm-5 is the same for
get-locl-size.cl, get-global-size.cl get-num-groups.cl, and
global-memory.cl piglits (and all of them pass on Turks).

 r600/lib/OVERRIDES_3.9                 |  1 -
 r600/lib/OVERRIDES_4.0                 |  1 -
 r600/lib/OVERRIDES_5.0                 |  1 -
 r600/lib/OVERRIDES_6.0                 |  1 -
 r600/lib/SOURCES                       |  2 +-
 r600/lib/SOURCES_3.9                   |  1 -
 r600/lib/SOURCES_4.0                   |  1 -
 r600/lib/SOURCES_5.0                   |  1 -
 r600/lib/SOURCES_6.0                   |  1 -
 r600/lib/workitem/get_local_size.39.ll | 20 --------------------
 r600/lib/workitem/get_local_size.cl    | 15 +++++++++++++++
 r600/lib/workitem/get_local_size.ll    | 20 --------------------
 12 files changed, 16 insertions(+), 49 deletions(-)
 delete mode 100644 r600/lib/workitem/get_local_size.39.ll
 create mode 100644 r600/lib/workitem/get_local_size.cl
 delete mode 100644 r600/lib/workitem/get_local_size.ll

diff --git a/r600/lib/OVERRIDES_3.9 b/r600/lib/OVERRIDES_3.9
index c055c6d..e1a6ae8 100644
--- a/r600/lib/OVERRIDES_3.9
+++ b/r600/lib/OVERRIDES_3.9
@@ -1,4 +1,3 @@
 synchronization/barrier_impl.ll
 workitem/get_global_size.ll
-workitem/get_local_size.ll
 workitem/get_num_groups.ll
diff --git a/r600/lib/OVERRIDES_4.0 b/r600/lib/OVERRIDES_4.0
index c055c6d..e1a6ae8 100644
--- a/r600/lib/OVERRIDES_4.0
+++ b/r600/lib/OVERRIDES_4.0
@@ -1,4 +1,3 @@
 synchronization/barrier_impl.ll
 workitem/get_global_size.ll
-workitem/get_local_size.ll
 workitem/get_num_groups.ll
diff --git a/r600/lib/OVERRIDES_5.0 b/r600/lib/OVERRIDES_5.0
index c055c6d..e1a6ae8 100644
--- a/r600/lib/OVERRIDES_5.0
+++ b/r600/lib/OVERRIDES_5.0
@@ -1,4 +1,3 @@
 synchronization/barrier_impl.ll
 workitem/get_global_size.ll
-workitem/get_local_size.ll
 workitem/get_num_groups.ll
diff --git a/r600/lib/OVERRIDES_6.0 b/r600/lib/OVERRIDES_6.0
index c055c6d..e1a6ae8 100644
--- a/r600/lib/OVERRIDES_6.0
+++ b/r600/lib/OVERRIDES_6.0
@@ -1,4 +1,3 @@
 synchronization/barrier_impl.ll
 workitem/get_global_size.ll
-workitem/get_local_size.ll
 workitem/get_num_groups.ll
diff --git a/r600/lib/SOURCES b/r600/lib/SOURCES
index e69be4a..75cf901 100644
--- a/r600/lib/SOURCES
+++ b/r600/lib/SOURCES
@@ -5,6 +5,6 @@ workitem/get_global_offset.cl
 workitem/get_group_id.cl
 workitem/get_global_size.ll
 workitem/get_local_id.cl
-workitem/get_local_size.ll
+workitem/get_local_size.cl
 workitem/get_num_groups.ll
 workitem/get_work_dim.cl
diff --git a/r600/lib/SOURCES_3.9 b/r600/lib/SOURCES_3.9
index ba09398..9f36052 100644
--- a/r600/lib/SOURCES_3.9
+++ b/r600/lib/SOURCES_3.9
@@ -15,5 +15,4 @@ image/write_imageui.cl
 image/write_image_impl.ll
 synchronization/barrier_impl.39.ll
 workitem/get_global_size.39.ll
-workitem/get_local_size.39.ll
 workitem/get_num_groups.39.ll
diff --git a/r600/lib/SOURCES_4.0 b/r600/lib/SOURCES_4.0
index 091990c..6ca2332 100644
--- a/r600/lib/SOURCES_4.0
+++ b/r600/lib/SOURCES_4.0
@@ -1,4 +1,3 @@
 synchronization/barrier_impl.39.ll
 workitem/get_global_size.39.ll
-workitem/get_local_size.39.ll
 workitem/get_num_groups.39.ll
diff --git a/r600/lib/SOURCES_5.0 b/r600/lib/SOURCES_5.0
index 091990c..6ca2332 100644
--- a/r600/lib/SOURCES_5.0
+++ b/r600/lib/SOURCES_5.0
@@ -1,4 +1,3 @@
 synchronization/barrier_impl.39.ll
 workitem/get_global_size.39.ll
-workitem/get_local_size.39.ll
 workitem/get_num_groups.39.ll
diff --git a/r600/lib/SOURCES_6.0 b/r600/lib/SOURCES_6.0
index 091990c..6ca2332 100644
--- a/r600/lib/SOURCES_6.0
+++ b/r600/lib/SOURCES_6.0
@@ -1,4 +1,3 @@
 synchronization/barrier_impl.39.ll
 workitem/get_global_size.39.ll
-workitem/get_local_size.39.ll
 workitem/get_num_groups.39.ll
diff --git a/r600/lib/workitem/get_local_size.39.ll b/r600/lib/workitem/get_local_size.39.ll
deleted file mode 100644
index c9f2c84..0000000
--- a/r600/lib/workitem/get_local_size.39.ll
+++ /dev/null
@@ -1,20 +0,0 @@
-declare i32 @llvm.r600.read.local.size.x() nounwind readnone
-declare i32 @llvm.r600.read.local.size.y() nounwind readnone
-declare i32 @llvm.r600.read.local.size.z() nounwind readnone
-
-target datalayout = "e-p:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"
-
-define i32 @get_local_size(i32 %dim) nounwind readnone alwaysinline {
-  switch i32 %dim, label %default [i32 0, label %x_dim i32 1, label %y_dim i32 2, label %z_dim]
-x_dim:
-  %x = call i32 @llvm.r600.read.local.size.x()
-  ret i32 %x
-y_dim:
-  %y = call i32 @llvm.r600.read.local.size.y()
-  ret i32 %y
-z_dim:
-  %z = call i32 @llvm.r600.read.local.size.z()
-  ret i32 %z
-default:
-  ret i32 1
-}
diff --git a/r600/lib/workitem/get_local_size.cl b/r600/lib/workitem/get_local_size.cl
new file mode 100644
index 0000000..89e2612
--- /dev/null
+++ b/r600/lib/workitem/get_local_size.cl
@@ -0,0 +1,15 @@
+#include <clc/clc.h>
+
+uint __clc_r600_get_local_size_x(void) __asm("llvm.r600.read.local.size.x");
+uint __clc_r600_get_local_size_y(void) __asm("llvm.r600.read.local.size.y");
+uint __clc_r600_get_local_size_z(void) __asm("llvm.r600.read.local.size.z");
+
+_CLC_DEF size_t get_local_size(uint dim)
+{
+	switch (dim) {
+	case 0: return __clc_r600_get_local_size_x();
+	case 1: return __clc_r600_get_local_size_y();
+	case 2: return __clc_r600_get_local_size_z();
+	default: return 1;
+	}
+}
diff --git a/r600/lib/workitem/get_local_size.ll b/r600/lib/workitem/get_local_size.ll
deleted file mode 100644
index 04ce076..0000000
--- a/r600/lib/workitem/get_local_size.ll
+++ /dev/null
@@ -1,20 +0,0 @@
-declare i32 @llvm.r600.read.local.size.x() nounwind readnone
-declare i32 @llvm.r600.read.local.size.y() nounwind readnone
-declare i32 @llvm.r600.read.local.size.z() nounwind readnone
-
-target datalayout = "e-p:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5"
-
-define i32 @get_local_size(i32 %dim) nounwind readnone alwaysinline {
-  switch i32 %dim, label %default [i32 0, label %x_dim i32 1, label %y_dim i32 2, label %z_dim]
-x_dim:
-  %x = call i32 @llvm.r600.read.local.size.x()
-  ret i32 %x
-y_dim:
-  %y = call i32 @llvm.r600.read.local.size.y()
-  ret i32 %y
-z_dim:
-  %z = call i32 @llvm.r600.read.local.size.z()
-  ret i32 %z
-default:
-  ret i32 1
-}
-- 
2.18.1



More information about the Libclc-dev mailing list