@@ -683,6 +683,30 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
return Builder.CreateInsertElement(I0, A, 1);
}
+ case AMDGPU::BI__builtin_amdgcn_image_load_2d_f32_i32: {
+llvm::Type *RetTy = llvm::Type::getFloatTy(Builder.getContext());
+
@@ -635,5 +635,10 @@ TARGET_BUILTIN(__builtin_amdgcn_bitop3_b16, "IUi",
"nc", "bitop3-insts")
TARGET_BUILTIN(__builtin_amdgcn_cvt_sr_bf16_f32, "V2yV2yfUiIb", "nc",
"f32-to-f16bf16-cvt-sr-insts")
TARGET_BUILTIN(__builtin_amdgcn_cvt_sr_f16_f32, "V2hV2hfUiIb", "nc",
"f32-to-
@@ -683,6 +683,30 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
return Builder.CreateInsertElement(I0, A, 1);
}
+ case AMDGPU::BI__builtin_amdgcn_image_load_2d_f32_i32: {
+llvm::Type *RetTy = llvm::Type::getFloatTy(Builder.getContext());
+
@@ -0,0 +1,31 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
UTC_ARGS: --version 5
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown %s -emit-llvm -o - |
FileCheck %s
ranapratap55 wrote:
done.
https://github.com/llvm/llvm-pr
@@ -683,6 +683,30 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
return Builder.CreateInsertElement(I0, A, 1);
}
+ case AMDGPU::BI__builtin_amdgcn_image_load_2d_f32_i32: {
+llvm::Type *RetTy = llvm::Type::getFloatTy(Builder.getContext());
+
@@ -635,5 +635,10 @@ TARGET_BUILTIN(__builtin_amdgcn_bitop3_b16, "IUi",
"nc", "bitop3-insts")
TARGET_BUILTIN(__builtin_amdgcn_cvt_sr_bf16_f32, "V2yV2yfUiIb", "nc",
"f32-to-f16bf16-cvt-sr-insts")
TARGET_BUILTIN(__builtin_amdgcn_cvt_sr_f16_f32, "V2hV2hfUiIb", "nc",
"f32-to-
@@ -0,0 +1,31 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
UTC_ARGS: --version 5
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown %s -emit-llvm -o - |
FileCheck %s
+
+#pragma OPENCL EXTENSION cl_khr_fp64:enable
+
+typedef int v8i __attribut
@@ -683,6 +683,30 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
return Builder.CreateInsertElement(I0, A, 1);
}
+ case AMDGPU::BI__builtin_amdgcn_image_load_2d_f32_i32: {
+llvm::Type *RetTy = llvm::Type::getFloatTy(Builder.getContext());
+
@@ -0,0 +1,31 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
UTC_ARGS: --version 5
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown %s -emit-llvm -o - |
FileCheck %s
+
+#pragma OPENCL EXTENSION cl_khr_fp64:enable
+
+typedef int v8i __attribut
@@ -0,0 +1,31 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
UTC_ARGS: --version 5
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown %s -emit-llvm -o - |
FileCheck %s
+
+#pragma OPENCL EXTENSION cl_khr_fp64:enable
+
+typedef int v8i __attribut
@@ -0,0 +1,31 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
UTC_ARGS: --version 5
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown %s -emit-llvm -o - |
FileCheck %s
+
+#pragma OPENCL EXTENSION cl_khr_fp64:enable
ranapratap55
https://github.com/ranapratap55 updated
https://github.com/llvm/llvm-project/pull/140210
>From d1571dd53f157c9d4180c51e709d9bed0ba00136 Mon Sep 17 00:00:00 2001
From: ranapratap55
Date: Fri, 16 May 2025 12:50:09 +0530
Subject: [PATCH 1/2] [WIP][AMDGPU] Support for type inferring image load/stor
https://github.com/ranapratap55 edited
https://github.com/llvm/llvm-project/pull/140210
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/ranapratap55 closed
https://github.com/llvm/llvm-project/pull/69567
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/ranapratap55 updated
https://github.com/llvm/llvm-project/pull/69567
>From bd6e1449bd098d8348cf1402ad875e79cbc274b5 Mon Sep 17 00:00:00 2001
From: ranapratap55
Date: Thu, 19 Oct 2023 12:52:13 +0530
Subject: [PATCH] [AMDGPU] Lower __builtin_read_exec_hi to use amdgcn_ballot
-
https://github.com/ranapratap55 updated
https://github.com/llvm/llvm-project/pull/69567
>From ebc8ebdebf707f94723b1fe0ee1a1b6afe5dff49 Mon Sep 17 00:00:00 2001
From: ranapratap55
Date: Thu, 19 Oct 2023 12:52:13 +0530
Subject: [PATCH] [AMDGPU] Lower __builtin_read_exec_hi to use amdgcn_ballot
-
@@ -7995,15 +7995,24 @@ enum SpecialRegisterAccessKind {
Write,
};
+// Generates the IR for __builtin_read_exec_*.
+// Lowers the builtin to amdgcn_ballot intrinsic.
static Value *EmitAMDGCNBallotForExec(CodeGenFunction &CGF, const CallExpr *E,
@@ -21,6 +23,28 @@ void test_ballot_wave32_target_attr(global uint* out, int a,
int b)
*out = __builtin_amdgcn_ballot_w32(a == b);
}
+// CHECK-LABEL: @test_read_exec(
+// CHECK: call i64 @llvm.amdgcn.ballot.i64(i1 true)
+void test_read_exec(global uint* out) {
+ *out = __b
https://github.com/ranapratap55 updated
https://github.com/llvm/llvm-project/pull/69567
>From 8a5dfe62b7ce84d49f6684563f04122b75fc35ef Mon Sep 17 00:00:00 2001
From: ranapratap55
Date: Thu, 19 Oct 2023 12:52:13 +0530
Subject: [PATCH] [AMDGPU] Lower __builtin_read_exec_hi to use amdgcn_ballot
-
https://github.com/ranapratap55 updated
https://github.com/llvm/llvm-project/pull/69567
>From 65c806a4c1703214fa7eaebecfdaa200b6d0d205 Mon Sep 17 00:00:00 2001
From: ranapratap55
Date: Thu, 19 Oct 2023 12:52:13 +0530
Subject: [PATCH] [AMDGPU] Lower __builtin_read_exec_hi to use amdgcn_ballot
-
https://github.com/ranapratap55 updated
https://github.com/llvm/llvm-project/pull/69567
>From c2ed656fa149a9cb60fb43eb34f4b20186166b34 Mon Sep 17 00:00:00 2001
From: ranapratap55
Date: Thu, 19 Oct 2023 12:52:13 +0530
Subject: [PATCH] [AMDGPU] Lower __builtin_read_exec_hi to use amdgcn_ballot
-
@@ -526,7 +526,9 @@ void test_read_exec_lo(global uint* out) {
// CHECK: declare i32 @llvm.amdgcn.ballot.i32(i1)
#[[$NOUNWIND_READONLY:[0-9]+]]
// CHECK-LABEL: @test_read_exec_hi(
-// CHECK: call i32 @llvm.amdgcn.ballot.i32(i1 true)
+// CHECK: call i64 @llvm.amdgcn.ballot.i64
@@ -7997,14 +7997,26 @@ enum SpecialRegisterAccessKind {
static Value *EmitAMDGCNBallotForExec(CodeGenFunction &CGF, const CallExpr *E,
llvm::Type *RegisterType,
- llvm::Type *ValueType) {
+
@@ -7997,14 +7997,26 @@ enum SpecialRegisterAccessKind {
static Value *EmitAMDGCNBallotForExec(CodeGenFunction &CGF, const CallExpr *E,
llvm::Type *RegisterType,
- llvm::Type *ValueType) {
+
https://github.com/ranapratap55 updated
https://github.com/llvm/llvm-project/pull/69567
>From 536e4b5912f976b295bc2b507e4181c8a65f0d12 Mon Sep 17 00:00:00 2001
From: ranapratap55
Date: Thu, 19 Oct 2023 12:52:13 +0530
Subject: [PATCH] [AMDGPU] Lower __builtin_read_exec_hi to use amdgcn_ballot
-
https://github.com/ranapratap55 edited
https://github.com/llvm/llvm-project/pull/69567
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/ranapratap55 edited
https://github.com/llvm/llvm-project/pull/69567
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/ranapratap55 updated
https://github.com/llvm/llvm-project/pull/69567
>From 19582446dbabffb0b25f9fa8b8b62a06ce6a4c66 Mon Sep 17 00:00:00 2001
From: ranapratap55
Date: Thu, 19 Oct 2023 12:52:13 +0530
Subject: [PATCH] [AMDGPU] Lower __builtin_read_exec_hi to use amdgcn_ballot
-
https://github.com/ranapratap55 created
https://github.com/llvm/llvm-project/pull/69567
Currently __builtin_read_exec_hi lowers to llvm.read_register, this patch
lowers it to use amdgcn_ballot.
>From 340e633da9e3ab10efc0c0d430b9546cd2f19cfe Mon Sep 17 00:00:00 2001
From: ranapratap55
Date: Th
29 matches
Mail list logo
