aboutsummaryrefslogtreecommitdiff
path: root/llvm/test/CodeGen/WebAssembly
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/test/CodeGen/WebAssembly')
-rw-r--r--llvm/test/CodeGen/WebAssembly/int-mac-reduction-loops.ll208
-rw-r--r--llvm/test/CodeGen/WebAssembly/simd-relaxed-dot.ll104
2 files changed, 312 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/WebAssembly/int-mac-reduction-loops.ll b/llvm/test/CodeGen/WebAssembly/int-mac-reduction-loops.ll
index 04a2268..314e1b4 100644
--- a/llvm/test/CodeGen/WebAssembly/int-mac-reduction-loops.ll
+++ b/llvm/test/CodeGen/WebAssembly/int-mac-reduction-loops.ll
@@ -1,5 +1,6 @@
; RUN: opt -mattr=+simd128 -passes=loop-vectorize %s | llc -mtriple=wasm32 -mattr=+simd128 -verify-machineinstrs -o - | FileCheck %s
; RUN: opt -mattr=+simd128 -passes=loop-vectorize -vectorizer-maximize-bandwidth %s | llc -mtriple=wasm32 -mattr=+simd128 -verify-machineinstrs -o - | FileCheck %s --check-prefix=MAX-BANDWIDTH
+; RUN: opt -mattr=+simd128,+relaxed-simd -passes=loop-vectorize -vectorizer-maximize-bandwidth %s | llc -mtriple=wasm32 -mattr=+simd128,+relaxed-simd -verify-machineinstrs -o - | FileCheck %s --check-prefix=RELAXED-MAX-BANDWIDTH
target triple = "wasm32"
@@ -23,6 +24,10 @@ define hidden i32 @i32_mac_s8(ptr nocapture noundef readonly %a, ptr nocapture n
; MAX-BANDWIDTH: i32x4.add
; MAX-BANDWIDTH: i32x4.add
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: i32x4.relaxed_dot_i8x16_i7x16_add_s
+
entry:
%cmp7.not = icmp eq i32 %N, 0
br i1 %cmp7.not, label %for.cond.cleanup, label %for.body
@@ -47,6 +52,109 @@ for.body: ; preds = %entry, %for.body
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}
+define hidden i32 @i32_mac_u8_s8(ptr nocapture noundef readonly %a, ptr nocapture noundef readonly %b, i32 noundef %N) {
+; CHECK-LABEL: i32_mac_u8_s8:
+; CHECK: loop
+; CHECK: v128.load32_zero
+; CHECK: i16x8.extend_low_i8x16_u
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: v128.load32_zero
+; CHECK: i16x8.extend_low_i8x16_s
+; CHECK: i32x4.extend_low_i16x8_s
+; CHECK: i32x4.mul
+; CHECK: i32x4.add
+
+; MAX-BANDWIDTH: loop
+; MAX-BANDWIDTH: v128.load
+; MAX-BANDWIDTH: i8x16.shuffle 12, 13, 14, 15, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; MAX-BANDWIDTH: i16x8.extend_low_i8x16_u
+; MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
+; MAX-BANDWIDTH: v128.load
+; MAX-BANDWIDTH: i8x16.shuffle 12, 13, 14, 15, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; MAX-BANDWIDTH: i16x8.extend_low_i8x16_s
+; MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
+; MAX-BANDWIDTH: i32x4.mul
+; MAX-BANDWIDTH: i32x4.add
+; MAX-BANDWIDTH: i8x16.shuffle 8, 9, 10, 11, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; MAX-BANDWIDTH: i16x8.extend_low_i8x16_u
+; MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
+; MAX-BANDWIDTH: i8x16.shuffle 8, 9, 10, 11, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; MAX-BANDWIDTH: i16x8.extend_low_i8x16_s
+; MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
+; MAX-BANDWIDTH: i32x4.mul
+; MAX-BANDWIDTH: i32x4.add
+; MAX-BANDWIDTH: i8x16.shuffle 4, 5, 6, 7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; MAX-BANDWIDTH: i16x8.extend_low_i8x16_u
+; MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
+; MAX-BANDWIDTH: i8x16.shuffle 4, 5, 6, 7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; MAX-BANDWIDTH: i16x8.extend_low_i8x16_s
+; MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
+; MAX-BANDWIDTH: i32x4.mul
+; MAX-BANDWIDTH: i32x4.add
+; MAX-BANDWIDTH: i16x8.extend_low_i8x16_u
+; MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
+; MAX-BANDWIDTH: i16x8.extend_low_i8x16_s
+; MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
+; MAX-BANDWIDTH: i32x4.mul
+; MAX-BANDWIDTH: i32x4.add
+
+; RELAXED-MAX-BANDWIDTH: loop
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 12, 13, 14, 15, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; RELAXED-MAX-BANDWIDTH: i16x8.extend_low_i8x16_u
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 12, 13, 14, 15, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; RELAXED-MAX-BANDWIDTH: i16x8.extend_low_i8x16_s
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
+; RELAXED-MAX-BANDWIDTH: i32x4.mul
+; RELAXED-MAX-BANDWIDTH: i32x4.add
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 8, 9, 10, 11, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; RELAXED-MAX-BANDWIDTH: i16x8.extend_low_i8x16_u
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 8, 9, 10, 11, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; RELAXED-MAX-BANDWIDTH: i16x8.extend_low_i8x16_s
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
+; RELAXED-MAX-BANDWIDTH: i32x4.mul
+; RELAXED-MAX-BANDWIDTH: i32x4.add
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 4, 5, 6, 7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; RELAXED-MAX-BANDWIDTH: i16x8.extend_low_i8x16_u
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 4, 5, 6, 7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; RELAXED-MAX-BANDWIDTH: i16x8.extend_low_i8x16_s
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
+; RELAXED-MAX-BANDWIDTH: i32x4.mul
+; RELAXED-MAX-BANDWIDTH: i32x4.add
+; RELAXED-MAX-BANDWIDTH: i16x8.extend_low_i8x16_u
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
+; RELAXED-MAX-BANDWIDTH: i16x8.extend_low_i8x16_s
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
+; RELAXED-MAX-BANDWIDTH: i32x4.mul
+; RELAXED-MAX-BANDWIDTH: i32x4.add
+entry:
+ %cmp7.not = icmp eq i32 %N, 0
+ br i1 %cmp7.not, label %for.cond.cleanup, label %for.body
+
+for.cond.cleanup: ; preds = %for.body, %entry
+ %res.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
+ ret i32 %res.0.lcssa
+
+for.body: ; preds = %entry, %for.body
+ %i.09 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
+ %res.08 = phi i32 [ %add, %for.body ], [ 0, %entry ]
+ %arrayidx = getelementptr inbounds i8, ptr %a, i32 %i.09
+ %0 = load i8, ptr %arrayidx, align 1
+ %conv = sext i8 %0 to i32
+ %arrayidx1 = getelementptr inbounds i8, ptr %b, i32 %i.09
+ %1 = load i8, ptr %arrayidx1, align 1
+ %conv2 = zext i8 %1 to i32
+ %mul = mul nsw i32 %conv2, %conv
+ %add = add nsw i32 %mul, %res.08
+ %inc = add nuw i32 %i.09, 1
+ %exitcond.not = icmp eq i32 %inc, %N
+ br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
+}
+
define hidden i32 @i32_mac_s16(ptr nocapture noundef readonly %a, ptr nocapture noundef readonly %b, i32 noundef %N) {
; CHECK-LABEL: i32_mac_s16:
; CHECK: i32x4.load16x4_s 0:p2align=1
@@ -57,6 +165,12 @@ define hidden i32 @i32_mac_s16(ptr nocapture noundef readonly %a, ptr nocapture
; MAX-BANDWIDTH: v128.load
; MAX-BANDWIDTH: v128.load
; MAX-BANDWIDTH: i32x4.dot_i16x8_s
+; MAX-BANDWIDTH: i32x4.add
+
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: i32x4.dot_i16x8_s
+; RELAXED-MAX-BANDWIDTH: i32x4.add
entry:
%cmp7.not = icmp eq i32 %N, 0
@@ -116,6 +230,31 @@ define hidden i64 @i64_mac_s16(ptr nocapture noundef readonly %a, ptr nocapture
; MAX-BANDWIDTH: i64x2.extmul_low_i32x4_s
; MAX-BANDWIDTH: i64x2.add
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 12, 13, 14, 15, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 12, 13, 14, 15, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
+; RELAXED-MAX-BANDWIDTH: i64x2.extmul_low_i32x4_s
+; RELAXED-MAX-BANDWIDTH: i64x2.add
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 8, 9, 10, 11, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 8, 9, 10, 11, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
+; RELAXED-MAX-BANDWIDTH: i64x2.extmul_low_i32x4_s
+; RELAXED-MAX-BANDWIDTH: i64x2.add
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 4, 5, 6, 7, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 4, 5, 6, 7, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
+; RELAXED-MAX-BANDWIDTH: i64x2.extmul_low_i32x4_s
+; RELAXED-MAX-BANDWIDTH: i64x2.add
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
+; RELAXED-MAX-BANDWIDTH: i64x2.extmul_low_i32x4_s
+; RELAXED-MAX-BANDWIDTH: i64x2.add
+
entry:
%cmp7.not = icmp eq i32 %N, 0
br i1 %cmp7.not, label %for.cond.cleanup, label %for.body
@@ -156,6 +295,14 @@ define hidden i64 @i64_mac_s32(ptr nocapture noundef readonly %a, ptr nocapture
; MAX-BANDWIDTH: i64x2.extend_low_i32x4_s
; MAX-BANDWIDTH: i64x2.add
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: i32x4.mul
+; RELAXED-MAX-BANDWIDTH: i64x2.extend_high_i32x4_s
+; RELAXED-MAX-BANDWIDTH: i64x2.add
+; RELAXED-MAX-BANDWIDTH: i64x2.extend_low_i32x4_s
+; RELAXED-MAX-BANDWIDTH: i64x2.add
+
entry:
%cmp6.not = icmp eq i32 %N, 0
br i1 %cmp6.not, label %for.cond.cleanup, label %for.body
@@ -197,6 +344,15 @@ define hidden i32 @i32_mac_u8(ptr nocapture noundef readonly %a, ptr nocapture n
; MAX-BANDWIDTH: i32x4.add
; MAX-BANDWIDTH: i32x4.add
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: i16x8.extmul_low_i8x16_u
+; RELAXED-MAX-BANDWIDTH: i32x4.extadd_pairwise_i16x8_u
+; RELAXED-MAX-BANDWIDTH: i16x8.extmul_high_i8x16_u
+; RELAXED-MAX-BANDWIDTH: i32x4.extadd_pairwise_i16x8_u
+; RELAXED-MAX-BANDWIDTH: i32x4.add
+; RELAXED-MAX-BANDWIDTH: i32x4.add
+
entry:
%cmp7.not = icmp eq i32 %N, 0
br i1 %cmp7.not, label %for.cond.cleanup, label %for.body
@@ -235,6 +391,13 @@ define hidden i32 @i32_mac_u16(ptr nocapture noundef readonly %a, ptr nocapture
; MAX-BANDWIDTH: i32x4.add
; MAX-BANDWIDTH: i32x4.add
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: i32x4.extmul_low_i16x8_u
+; RELAXED-MAX-BANDWIDTH: i32x4.extmul_high_i16x8_u
+; RELAXED-MAX-BANDWIDTH: i32x4.add
+; RELAXED-MAX-BANDWIDTH: i32x4.add
+
entry:
%cmp7.not = icmp eq i32 %N, 0
br i1 %cmp7.not, label %for.cond.cleanup, label %for.body
@@ -277,6 +440,17 @@ define hidden i32 @i32_mac_u16_s16(ptr nocapture noundef readonly %a, ptr nocapt
; MAX-BANDWIDTH: i32x4.add
; MAX-BANDWIDTH: i32x4.add
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_high_i16x8_s
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_high_i16x8_u
+; RELAXED-MAX-BANDWIDTH: i32x4.mul
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
+; RELAXED-MAX-BANDWIDTH: i32x4.mul
+; RELAXED-MAX-BANDWIDTH: i32x4.add
+; RELAXED-MAX-BANDWIDTH: i32x4.add
+
entry:
%cmp7.not = icmp eq i32 %N, 0
br i1 %cmp7.not, label %for.cond.cleanup, label %for.body
@@ -335,6 +509,32 @@ define hidden i64 @i64_mac_u16(ptr nocapture noundef readonly %a, ptr nocapture
; MAX-BANDWIDTH: i64x2.extmul_low_i32x4_u
; MAX-BANDWIDTH: i64x2.add
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 12, 13, 14, 15, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 12, 13, 14, 15, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
+; RELAXED-MAX-BANDWIDTH: i64x2.extmul_low_i32x4_u
+; RELAXED-MAX-BANDWIDTH: i64x2.add
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 8, 9, 10, 11, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 8, 9, 10, 11, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
+; RELAXED-MAX-BANDWIDTH: i64x2.extmul_low_i32x4_u
+; RELAXED-MAX-BANDWIDTH: i64x2.add
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 4, 5, 6, 7, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
+; RELAXED-MAX-BANDWIDTH: i8x16.shuffle 4, 5, 6, 7, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
+; RELAXED-MAX-BANDWIDTH: i64x2.extmul_low_i32x4_u
+; RELAXED-MAX-BANDWIDTH: i64x2.add
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
+; RELAXED-MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
+; RELAXED-MAX-BANDWIDTH: i64x2.extmul_low_i32x4_u
+; RELAXED-MAX-BANDWIDTH: i64x2.add
+
+
entry:
%cmp8.not = icmp eq i32 %N, 0
br i1 %cmp8.not, label %for.cond.cleanup, label %for.body
@@ -375,6 +575,14 @@ define hidden i64 @i64_mac_u32(ptr nocapture noundef readonly %a, ptr nocapture
; MAX-BANDWIDTH: i64x2.extend_low_i32x4_u
; MAX-BANDWIDTH: i64x2.add
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: v128.load
+; RELAXED-MAX-BANDWIDTH: i32x4.mul
+; RELAXED-MAX-BANDWIDTH: i64x2.extend_high_i32x4_u
+; RELAXED-MAX-BANDWIDTH: i64x2.add
+; RELAXED-MAX-BANDWIDTH: i64x2.extend_low_i32x4_u
+; RELAXED-MAX-BANDWIDTH: i64x2.add
+
entry:
%cmp6.not = icmp eq i32 %N, 0
br i1 %cmp6.not, label %for.cond.cleanup, label %for.body
diff --git a/llvm/test/CodeGen/WebAssembly/simd-relaxed-dot.ll b/llvm/test/CodeGen/WebAssembly/simd-relaxed-dot.ll
new file mode 100644
index 0000000..9716cbe
--- /dev/null
+++ b/llvm/test/CodeGen/WebAssembly/simd-relaxed-dot.ll
@@ -0,0 +1,104 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -mattr=+fp16,+simd128,+relaxed-simd | FileCheck %s
+
+target triple = "wasm32"
+; relaxed_dot stands for relaxed_dot_i8x16_i7x16_s, as in td
+; relaxed_dot_add stands for i32x4.relaxed_dot_i8x16_i7x16_add_s, as in td
+
+define <8 x i16> @relaxed_dot_sext_1(<16 x i8> %a, <16 x i8> %b) {
+; CHECK-LABEL: relaxed_dot_sext_1:
+; CHECK: .functype relaxed_dot_sext_1 (v128, v128) -> (v128)
+; CHECK-NEXT: # %bb.0:
+; CHECK-NEXT: i16x8.relaxed_dot_i8x16_i7x16_s $push0=, $0, $1
+; CHECK-NEXT: return $pop0
+ %sext1 = sext <16 x i8> %a to <16 x i16>
+ %sext2 = sext <16 x i8> %b to <16 x i16>
+ %mul = mul <16 x i16> %sext1, %sext2
+ %shuffle1 = shufflevector <16 x i16> %mul, <16 x i16> poison, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
+ %shuffle2 = shufflevector <16 x i16> %mul, <16 x i16> poison, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
+ %res = add <8 x i16> %shuffle1, %shuffle2
+ ret <8 x i16> %res
+}
+
+
+define <8 x i16> @relaxed_dot_sext_2(<16 x i8> %a, <16 x i8> %b) {
+; CHECK-LABEL: relaxed_dot_sext_2:
+; CHECK: .functype relaxed_dot_sext_2 (v128, v128) -> (v128)
+; CHECK-NEXT: # %bb.0:
+; CHECK-NEXT: i16x8.relaxed_dot_i8x16_i7x16_s $push0=, $0, $1
+; CHECK-NEXT: return $pop0
+ %sext1 = sext <16 x i8> %a to <16 x i16>
+ %sext2 = sext <16 x i8> %b to <16 x i16>
+ %mul = mul <16 x i16> %sext1, %sext2
+ %shuffle1 = shufflevector <16 x i16> %mul, <16 x i16> poison, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
+ %shuffle2 = shufflevector <16 x i16> %mul, <16 x i16> poison, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
+ %res = add <8 x i16> %shuffle2, %shuffle1
+ ret <8 x i16> %res
+}
+
+define <8 x i16> @relaxed_dot_sext_self(<16 x i8> %v) {
+; CHECK-LABEL: relaxed_dot_sext_self:
+; CHECK: .functype relaxed_dot_sext_self (v128) -> (v128)
+; CHECK-NEXT: # %bb.0:
+; CHECK-NEXT: i16x8.relaxed_dot_i8x16_i7x16_s $push0=, $0, $0
+; CHECK-NEXT: return $pop0
+ %sext = sext <16 x i8> %v to <16 x i16>
+ %mul = mul <16 x i16> %sext, %sext
+ %shuffle1 = shufflevector <16 x i16> %mul, <16 x i16> poison, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
+ %shuffle2 = shufflevector <16 x i16> %mul, <16 x i16> poison, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
+ %res = add <8 x i16> %shuffle1, %shuffle2
+ ret <8 x i16> %res
+}
+
+define <4 x i32> @relaxed_dot_add_from_relaxed_dot(<16 x i8> %a, <16 x i8> %b, <4 x i32> %c) {
+; CHECK-LABEL: relaxed_dot_add_from_relaxed_dot:
+; CHECK: .functype relaxed_dot_add_from_relaxed_dot (v128, v128, v128) -> (v128)
+; CHECK-NEXT: # %bb.0:
+; CHECK-NEXT: i32x4.relaxed_dot_i8x16_i7x16_add_s $push0=, $0, $1, $2
+; CHECK-NEXT: return $pop0
+ %relaxed_dot_call = call <8 x i16> @llvm.wasm.relaxed.dot.i8x16.i7x16.signed(<16 x i8> %a, <16 x i8> %b)
+ %sext = call <4 x i32> @llvm.wasm.extadd.pairwise.signed.v4i32(<8 x i16> %relaxed_dot_call)
+ %res = add <4 x i32> %sext, %c
+ ret <4 x i32> %res
+}
+
+; INFO: Negative test
+define <8 x i16> @relaxed_dot_zext(<16 x i8> %a, <16 x i8> %b) {
+; CHECK-LABEL: relaxed_dot_zext:
+; CHECK: .functype relaxed_dot_zext (v128, v128) -> (v128)
+; CHECK-NEXT: # %bb.0:
+; CHECK-NEXT: i16x8.extmul_low_i8x16_u $push6=, $0, $1
+; CHECK-NEXT: local.tee $push5=, $2=, $pop6
+; CHECK-NEXT: i16x8.extmul_high_i8x16_u $push4=, $0, $1
+; CHECK-NEXT: local.tee $push3=, $1=, $pop4
+; CHECK-NEXT: i8x16.shuffle $push1=, $pop5, $pop3, 0, 1, 4, 5, 8, 9, 12, 13, 16, 17, 20, 21, 24, 25, 28, 29
+; CHECK-NEXT: i8x16.shuffle $push0=, $2, $1, 2, 3, 6, 7, 10, 11, 14, 15, 18, 19, 22, 23, 26, 27, 30, 31
+; CHECK-NEXT: i16x8.add $push2=, $pop1, $pop0
+; CHECK-NEXT: return $pop2
+ %zext1 = zext <16 x i8> %a to <16 x i16>
+ %zext2 = zext <16 x i8> %b to <16 x i16>
+ %mul = mul <16 x i16> %zext1, %zext2
+ %shuffle1 = shufflevector <16 x i16> %mul, <16 x i16> poison, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
+ %shuffle2 = shufflevector <16 x i16> %mul, <16 x i16> poison, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
+ %res = add <8 x i16> %shuffle1, %shuffle2
+ ret <8 x i16> %res
+
+}
+
+; INFO: Negative test
+define <8 x i16> @relaxed_dot_wrong_shuffle(<16 x i8> %a, <16 x i8> %b) {
+; CHECK-LABEL: relaxed_dot_wrong_shuffle:
+; CHECK: .functype relaxed_dot_wrong_shuffle (v128, v128) -> (v128)
+; CHECK-NEXT: # %bb.0:
+; CHECK-NEXT: i16x8.extmul_low_i8x16_s $push1=, $0, $1
+; CHECK-NEXT: i16x8.extmul_high_i8x16_s $push0=, $0, $1
+; CHECK-NEXT: i16x8.add $push2=, $pop1, $pop0
+; CHECK-NEXT: return $pop2
+ %sext1 = sext <16 x i8> %a to <16 x i16>
+ %sext2 = sext <16 x i8> %b to <16 x i16>
+ %mul = mul <16 x i16> %sext1, %sext2
+ %shuffle1 = shufflevector <16 x i16> %mul, <16 x i16> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+ %shuffle2 = shufflevector <16 x i16> %mul, <16 x i16> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+ %res = add <8 x i16> %shuffle1, %shuffle2
+ ret <8 x i16> %res
+}
generated by cgit v1.1 at 2025-10-16 20:10:38 +0000