[PATCH] D155059: [AMDGPU][MC] Pre-commit tests for the noa16 intersect_ray instructions fix, D155057.

[Ivan Kosarev via Phabricator via llvm-commits]

kosarev created this revision.
Herald added subscribers: kerbowa, tpr, dstuttard, yaxunl, jvesely, kzhuravl.
Herald added a project: All.
kosarev requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

The added instructions are incorrectly encoded as a16 ones despite the
'noa16' modifiers.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D155059

Files:
  llvm/test/MC/AMDGPU/gfx1030_new.s
  llvm/test/MC/AMDGPU/gfx11_asm_mimg_features.s


Index: llvm/test/MC/AMDGPU/gfx11_asm_mimg_features.s
===================================================================
--- llvm/test/MC/AMDGPU/gfx11_asm_mimg_features.s
+++ llvm/test/MC/AMDGPU/gfx11_asm_mimg_features.s
@@ -328,6 +328,9 @@
 image_bvh_intersect_ray v[4:7], v[9:16], s[4:7] a16
 // GFX11: image_bvh_intersect_ray v[4:7], v[9:16], s[4:7] a16 ; encoding: [0x80,0x8f,0x65,0xf0,0x09,0x04,0x01,0x00]
 
+image_bvh_intersect_ray v[4:7], v[9:16], s[4:7] noa16
+// GFX11: image_bvh_intersect_ray v[4:7], v[9:16], s[4:7] a16 ; encoding: [0x80,0x8f,0x65,0xf0,0x09,0x04,0x01,0x00]
+
 image_bvh64_intersect_ray v[4:7], v[9:20], s[4:7]
 // GFX11: image_bvh64_intersect_ray v[4:7], v[9:20], s[4:7] ; encoding: [0x80,0x8f,0x68,0xf0,0x09,0x04,0x01,0x00]
 
@@ -340,6 +343,9 @@
 image_bvh_intersect_ray v[39:42], [v50, v46, v[20:22], v[40:42]], s[12:15] a16
 // GFX11: image_bvh_intersect_ray v[39:42], [v50, v46, v[20:22], v[40:42]], s[12:15] a16 ; encoding: [0x81,0x8f,0x65,0xf0,0x32,0x27,0x03,0x00,0x2e,0x14,0x28,0x00]
 
+image_bvh_intersect_ray v[39:42], [v50, v46, v[20:22], v[40:42]], s[12:15] noa16
+// GFX11: image_bvh_intersect_ray v[39:42], [v50, v46, v[20:22], v[40:42]], s[12:15] a16 ; encoding: [0x81,0x8f,0x65,0xf0,0x32,0x27,0x03,0x00,0x2e,0x14,0x28,0x00]
+
 image_bvh64_intersect_ray v[39:42], [v[50:51], v46, v[20:22], v[40:42], v[47:49]], s[12:15]
 // GFX11: image_bvh64_intersect_ray v[39:42], [v[50:51], v46, v[20:22], v[40:42], v[47:49]], s[12:15] ; encoding: [0x81,0x8f,0x68,0xf0,0x32,0x27,0x03,0x00,0x2e,0x14,0x28,0x2f]
 
Index: llvm/test/MC/AMDGPU/gfx1030_new.s
===================================================================
--- llvm/test/MC/AMDGPU/gfx1030_new.s
+++ llvm/test/MC/AMDGPU/gfx1030_new.s
@@ -90,6 +90,9 @@
 image_bvh_intersect_ray v[4:7], v[9:16], s[4:7] a16
 // GFX10: encoding: [0x01,0x9f,0x98,0xf1,0x09,0x04,0x01,0x40]
 
+image_bvh_intersect_ray v[4:7], v[9:16], s[4:7] noa16
+// GFX10: encoding: [0x01,0x9f,0x98,0xf1,0x09,0x04,0x01,0x40]
+
 image_bvh64_intersect_ray v[4:7], v[9:20], s[4:7]
 // GFX10: encoding: [0x01,0x9f,0x9c,0xf1,0x09,0x04,0x01,0x00]
 
@@ -102,6 +105,9 @@
 image_bvh_intersect_ray v[39:42], [v50, v46, v23, v17, v16, v15, v21, v20], s[12:15] a16
 // GFX10: encoding: [0x05,0x9f,0x98,0xf1,0x32,0x27,0x03,0x40,0x2e,0x17,0x11,0x10,0x0f,0x15,0x14,0x00]
 
+image_bvh_intersect_ray v[39:42], [v50, v46, v23, v17, v16, v15, v21, v20], s[12:15] noa16
+// GFX10: encoding: [0x05,0x9f,0x98,0xf1,0x32,0x27,0x03,0x40,0x2e,0x17,0x11,0x10,0x0f,0x15,0x14,0x00]
+
 image_bvh64_intersect_ray v[39:42], [v50, v46, v23, v17, v16, v15, v21, v20, v19, v37, v40, v42], s[12:15]
 // GFX10: encoding: [0x07,0x9f,0x9c,0xf1,0x32,0x27,0x03,0x00,0x2e,0x17,0x11,0x10,0x0f,0x15,0x14,0x13,0x25,0x28,0x2a,0x00]
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D155059.539451.patch
Type: text/x-patch
Size: 2743 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230712/27fd2435/attachment.bin>