[llvm-branch-commits] [llvm] [X86] Add atomic vector tests for unaligned >1 sizes. (PR #120387)
via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Thu Dec 19 08:42:46 PST 2024
https://github.com/jofrn updated https://github.com/llvm/llvm-project/pull/120387
>From f7691a8b3c3dccabc106ac21964ef5c86cda8c01 Mon Sep 17 00:00:00 2001
From: jofrn <jofernau at amd.com>
Date: Wed, 18 Dec 2024 03:40:32 -0500
Subject: [PATCH] [X86] Add atomic vector tests for unaligned >1 sizes.
Unaligned atomic vectors with size >1 are lowered to calls.
Adding their tests separately here.
commit-id:a06a5cc6
---
llvm/test/CodeGen/X86/atomic-load-store.ll | 253 +++++++++++++++++++++
1 file changed, 253 insertions(+)
diff --git a/llvm/test/CodeGen/X86/atomic-load-store.ll b/llvm/test/CodeGen/X86/atomic-load-store.ll
index f7a2cfd4c35f49..a57ae767859b10 100644
--- a/llvm/test/CodeGen/X86/atomic-load-store.ll
+++ b/llvm/test/CodeGen/X86/atomic-load-store.ll
@@ -146,6 +146,34 @@ define <1 x i64> @atomic_vec1_i64_align(ptr %x) nounwind {
ret <1 x i64> %ret
}
+define <1 x ptr> @atomic_vec1_ptr(ptr %x) nounwind {
+; CHECK3-LABEL: atomic_vec1_ptr:
+; CHECK3: ## %bb.0:
+; CHECK3-NEXT: pushq %rax
+; CHECK3-NEXT: movq %rdi, %rsi
+; CHECK3-NEXT: movq %rsp, %rdx
+; CHECK3-NEXT: movl $8, %edi
+; CHECK3-NEXT: movl $2, %ecx
+; CHECK3-NEXT: callq ___atomic_load
+; CHECK3-NEXT: movq (%rsp), %rax
+; CHECK3-NEXT: popq %rcx
+; CHECK3-NEXT: retq
+;
+; CHECK0-LABEL: atomic_vec1_ptr:
+; CHECK0: ## %bb.0:
+; CHECK0-NEXT: pushq %rax
+; CHECK0-NEXT: movq %rdi, %rsi
+; CHECK0-NEXT: movl $8, %edi
+; CHECK0-NEXT: movq %rsp, %rdx
+; CHECK0-NEXT: movl $2, %ecx
+; CHECK0-NEXT: callq ___atomic_load
+; CHECK0-NEXT: movq (%rsp), %rax
+; CHECK0-NEXT: popq %rcx
+; CHECK0-NEXT: retq
+ %ret = load atomic <1 x ptr>, ptr %x acquire, align 4
+ ret <1 x ptr> %ret
+}
+
define <1 x half> @atomic_vec1_half(ptr %x) {
; CHECK3-LABEL: atomic_vec1_half:
; CHECK3: ## %bb.0:
@@ -182,3 +210,228 @@ define <1 x double> @atomic_vec1_double_align(ptr %x) nounwind {
%ret = load atomic <1 x double>, ptr %x acquire, align 8
ret <1 x double> %ret
}
+
+define <1 x i64> @atomic_vec1_i64(ptr %x) nounwind {
+; CHECK3-LABEL: atomic_vec1_i64:
+; CHECK3: ## %bb.0:
+; CHECK3-NEXT: pushq %rax
+; CHECK3-NEXT: movq %rdi, %rsi
+; CHECK3-NEXT: movq %rsp, %rdx
+; CHECK3-NEXT: movl $8, %edi
+; CHECK3-NEXT: movl $2, %ecx
+; CHECK3-NEXT: callq ___atomic_load
+; CHECK3-NEXT: movq (%rsp), %rax
+; CHECK3-NEXT: popq %rcx
+; CHECK3-NEXT: retq
+;
+; CHECK0-LABEL: atomic_vec1_i64:
+; CHECK0: ## %bb.0:
+; CHECK0-NEXT: pushq %rax
+; CHECK0-NEXT: movq %rdi, %rsi
+; CHECK0-NEXT: movl $8, %edi
+; CHECK0-NEXT: movq %rsp, %rdx
+; CHECK0-NEXT: movl $2, %ecx
+; CHECK0-NEXT: callq ___atomic_load
+; CHECK0-NEXT: movq (%rsp), %rax
+; CHECK0-NEXT: popq %rcx
+; CHECK0-NEXT: retq
+ %ret = load atomic <1 x i64>, ptr %x acquire, align 4
+ ret <1 x i64> %ret
+}
+
+define <1 x double> @atomic_vec1_double(ptr %x) nounwind {
+; CHECK3-LABEL: atomic_vec1_double:
+; CHECK3: ## %bb.0:
+; CHECK3-NEXT: pushq %rax
+; CHECK3-NEXT: movq %rdi, %rsi
+; CHECK3-NEXT: movq %rsp, %rdx
+; CHECK3-NEXT: movl $8, %edi
+; CHECK3-NEXT: movl $2, %ecx
+; CHECK3-NEXT: callq ___atomic_load
+; CHECK3-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
+; CHECK3-NEXT: popq %rax
+; CHECK3-NEXT: retq
+;
+; CHECK0-LABEL: atomic_vec1_double:
+; CHECK0: ## %bb.0:
+; CHECK0-NEXT: pushq %rax
+; CHECK0-NEXT: movq %rdi, %rsi
+; CHECK0-NEXT: movl $8, %edi
+; CHECK0-NEXT: movq %rsp, %rdx
+; CHECK0-NEXT: movl $2, %ecx
+; CHECK0-NEXT: callq ___atomic_load
+; CHECK0-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
+; CHECK0-NEXT: popq %rax
+; CHECK0-NEXT: retq
+ %ret = load atomic <1 x double>, ptr %x acquire, align 4
+ ret <1 x double> %ret
+}
+
+define <2 x i32> @atomic_vec2_i32(ptr %x) nounwind {
+; CHECK3-LABEL: atomic_vec2_i32:
+; CHECK3: ## %bb.0:
+; CHECK3-NEXT: pushq %rax
+; CHECK3-NEXT: movq %rdi, %rsi
+; CHECK3-NEXT: movq %rsp, %rdx
+; CHECK3-NEXT: movl $8, %edi
+; CHECK3-NEXT: movl $2, %ecx
+; CHECK3-NEXT: callq ___atomic_load
+; CHECK3-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
+; CHECK3-NEXT: popq %rax
+; CHECK3-NEXT: retq
+;
+; CHECK0-LABEL: atomic_vec2_i32:
+; CHECK0: ## %bb.0:
+; CHECK0-NEXT: pushq %rax
+; CHECK0-NEXT: movq %rdi, %rsi
+; CHECK0-NEXT: movl $8, %edi
+; CHECK0-NEXT: movq %rsp, %rdx
+; CHECK0-NEXT: movl $2, %ecx
+; CHECK0-NEXT: callq ___atomic_load
+; CHECK0-NEXT: movq {{.*#+}} xmm0 = mem[0],zero
+; CHECK0-NEXT: popq %rax
+; CHECK0-NEXT: retq
+ %ret = load atomic <2 x i32>, ptr %x acquire, align 4
+ ret <2 x i32> %ret
+}
+
+define <4 x float> @atomic_vec4_float_align(ptr %x) nounwind {
+; CHECK-LABEL: atomic_vec4_float_align:
+; CHECK: ## %bb.0:
+; CHECK-NEXT: pushq %rax
+; CHECK-NEXT: movl $2, %esi
+; CHECK-NEXT: callq ___atomic_load_16
+; CHECK-NEXT: movq %rdx, %xmm1
+; CHECK-NEXT: movq %rax, %xmm0
+; CHECK-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; CHECK-NEXT: popq %rax
+; CHECK-NEXT: retq
+ %ret = load atomic <4 x float>, ptr %x acquire, align 16
+ ret <4 x float> %ret
+}
+
+define <4 x float> @atomic_vec4_float(ptr %x) nounwind {
+; CHECK3-LABEL: atomic_vec4_float:
+; CHECK3: ## %bb.0:
+; CHECK3-NEXT: subq $24, %rsp
+; CHECK3-NEXT: movq %rdi, %rsi
+; CHECK3-NEXT: movq %rsp, %rdx
+; CHECK3-NEXT: movl $16, %edi
+; CHECK3-NEXT: movl $2, %ecx
+; CHECK3-NEXT: callq ___atomic_load
+; CHECK3-NEXT: movaps (%rsp), %xmm0
+; CHECK3-NEXT: addq $24, %rsp
+; CHECK3-NEXT: retq
+;
+; CHECK0-LABEL: atomic_vec4_float:
+; CHECK0: ## %bb.0:
+; CHECK0-NEXT: subq $24, %rsp
+; CHECK0-NEXT: movq %rdi, %rsi
+; CHECK0-NEXT: movl $16, %edi
+; CHECK0-NEXT: movq %rsp, %rdx
+; CHECK0-NEXT: movl $2, %ecx
+; CHECK0-NEXT: callq ___atomic_load
+; CHECK0-NEXT: movaps (%rsp), %xmm0
+; CHECK0-NEXT: addq $24, %rsp
+; CHECK0-NEXT: retq
+ %ret = load atomic <4 x float>, ptr %x acquire, align 4
+ ret <4 x float> %ret
+}
+
+define <8 x double> @atomic_vec8_double(ptr %x) nounwind {
+; CHECK3-LABEL: atomic_vec8_double:
+; CHECK3: ## %bb.0:
+; CHECK3-NEXT: subq $72, %rsp
+; CHECK3-NEXT: movq %rdi, %rsi
+; CHECK3-NEXT: movq %rsp, %rdx
+; CHECK3-NEXT: movl $64, %edi
+; CHECK3-NEXT: movl $2, %ecx
+; CHECK3-NEXT: callq ___atomic_load
+; CHECK3-NEXT: movaps (%rsp), %xmm0
+; CHECK3-NEXT: movaps {{[0-9]+}}(%rsp), %xmm1
+; CHECK3-NEXT: movaps {{[0-9]+}}(%rsp), %xmm2
+; CHECK3-NEXT: movaps {{[0-9]+}}(%rsp), %xmm3
+; CHECK3-NEXT: addq $72, %rsp
+; CHECK3-NEXT: retq
+;
+; CHECK0-LABEL: atomic_vec8_double:
+; CHECK0: ## %bb.0:
+; CHECK0-NEXT: subq $72, %rsp
+; CHECK0-NEXT: movq %rdi, %rsi
+; CHECK0-NEXT: movl $64, %edi
+; CHECK0-NEXT: movq %rsp, %rdx
+; CHECK0-NEXT: movl $2, %ecx
+; CHECK0-NEXT: callq ___atomic_load
+; CHECK0-NEXT: movapd (%rsp), %xmm0
+; CHECK0-NEXT: movapd {{[0-9]+}}(%rsp), %xmm1
+; CHECK0-NEXT: movapd {{[0-9]+}}(%rsp), %xmm2
+; CHECK0-NEXT: movapd {{[0-9]+}}(%rsp), %xmm3
+; CHECK0-NEXT: addq $72, %rsp
+; CHECK0-NEXT: retq
+ %ret = load atomic <8 x double>, ptr %x acquire, align 4
+ ret <8 x double> %ret
+}
+
+define <16 x bfloat> @atomic_vec16_bfloat(ptr %x) nounwind {
+; CHECK3-LABEL: atomic_vec16_bfloat:
+; CHECK3: ## %bb.0:
+; CHECK3-NEXT: subq $40, %rsp
+; CHECK3-NEXT: movq %rdi, %rsi
+; CHECK3-NEXT: movq %rsp, %rdx
+; CHECK3-NEXT: movl $32, %edi
+; CHECK3-NEXT: movl $2, %ecx
+; CHECK3-NEXT: callq ___atomic_load
+; CHECK3-NEXT: movaps (%rsp), %xmm0
+; CHECK3-NEXT: movaps {{[0-9]+}}(%rsp), %xmm1
+; CHECK3-NEXT: addq $40, %rsp
+; CHECK3-NEXT: retq
+;
+; CHECK0-LABEL: atomic_vec16_bfloat:
+; CHECK0: ## %bb.0:
+; CHECK0-NEXT: subq $40, %rsp
+; CHECK0-NEXT: movq %rdi, %rsi
+; CHECK0-NEXT: movl $32, %edi
+; CHECK0-NEXT: movq %rsp, %rdx
+; CHECK0-NEXT: movl $2, %ecx
+; CHECK0-NEXT: callq ___atomic_load
+; CHECK0-NEXT: movaps (%rsp), %xmm0
+; CHECK0-NEXT: movaps {{[0-9]+}}(%rsp), %xmm1
+; CHECK0-NEXT: addq $40, %rsp
+; CHECK0-NEXT: retq
+ %ret = load atomic <16 x bfloat>, ptr %x acquire, align 4
+ ret <16 x bfloat> %ret
+}
+
+define <32 x half> @atomic_vec32_half(ptr %x) nounwind {
+; CHECK3-LABEL: atomic_vec32_half:
+; CHECK3: ## %bb.0:
+; CHECK3-NEXT: subq $72, %rsp
+; CHECK3-NEXT: movq %rdi, %rsi
+; CHECK3-NEXT: movq %rsp, %rdx
+; CHECK3-NEXT: movl $64, %edi
+; CHECK3-NEXT: movl $2, %ecx
+; CHECK3-NEXT: callq ___atomic_load
+; CHECK3-NEXT: movaps (%rsp), %xmm0
+; CHECK3-NEXT: movaps {{[0-9]+}}(%rsp), %xmm1
+; CHECK3-NEXT: movaps {{[0-9]+}}(%rsp), %xmm2
+; CHECK3-NEXT: movaps {{[0-9]+}}(%rsp), %xmm3
+; CHECK3-NEXT: addq $72, %rsp
+; CHECK3-NEXT: retq
+;
+; CHECK0-LABEL: atomic_vec32_half:
+; CHECK0: ## %bb.0:
+; CHECK0-NEXT: subq $72, %rsp
+; CHECK0-NEXT: movq %rdi, %rsi
+; CHECK0-NEXT: movl $64, %edi
+; CHECK0-NEXT: movq %rsp, %rdx
+; CHECK0-NEXT: movl $2, %ecx
+; CHECK0-NEXT: callq ___atomic_load
+; CHECK0-NEXT: movaps (%rsp), %xmm0
+; CHECK0-NEXT: movaps {{[0-9]+}}(%rsp), %xmm1
+; CHECK0-NEXT: movaps {{[0-9]+}}(%rsp), %xmm2
+; CHECK0-NEXT: movaps {{[0-9]+}}(%rsp), %xmm3
+; CHECK0-NEXT: addq $72, %rsp
+; CHECK0-NEXT: retq
+ %ret = load atomic <32 x half>, ptr %x acquire, align 4
+ ret <32 x half> %ret
+}
More information about the llvm-branch-commits
mailing list