diff --git a/ggml/src/ggml-cpu/simd-mappings.h b/ggml/src/ggml-cpu/simd-mappings.h
index fca5119e1a13..7d8486edbf6a 100644
--- a/ggml/src/ggml-cpu/simd-mappings.h
+++ b/ggml/src/ggml-cpu/simd-mappings.h
@@ -26,6 +26,23 @@ extern "C" {
 // simd mappings
 //
 
+// Force full unrolling of a loop with a compile-time constant trip count.
+//
+// The generic SIMD kernels below hold their vector operands and accumulators in
+// small arrays indexed by the inner loop counter (`for (j = 0; j < GGML_F32_ARR; j++)`).
+// Those arrays only stay in registers if the loop is unrolled: GCC does that at
+// -O3, but not at -O2 (the level used by RelWithDebInfo builds), where the
+// arrays are left in memory and every vector operation pays a load/store round
+// trip to the stack. Unrolling explicitly makes the codegen independent of the
+// optimization level.
+#if (defined(__clang__) && __clang_major__ >= 9) || (!defined(__clang__) && defined(__GNUC__) && __GNUC__ >= 8)
+    #define GGML_DO_PRAGMA_(x) _Pragma(#x)
+    #define GGML_DO_PRAGMA(x)  GGML_DO_PRAGMA_(x)
+    #define GGML_UNROLL(n)     GGML_DO_PRAGMA(GCC unroll n)
+#else
+    #define GGML_UNROLL(n)
+#endif
+
 // FP16 to FP32 conversion
 
 // 16-bit float
diff --git a/ggml/src/ggml-cpu/vec.cpp b/ggml/src/ggml-cpu/vec.cpp
index ff2b636df86c..8a49645bc223 100644
--- a/ggml/src/ggml-cpu/vec.cpp
+++ b/ggml/src/ggml-cpu/vec.cpp
@@ -109,6 +109,7 @@ void ggml_vec_dot_f32(int n, float * GGML_RESTRICT s, size_t bs, const float * G
         GGML_F32_VEC ay[GGML_F32_ARR];
 
         for (int i = 0; i < np; i += GGML_F32_STEP) {
+            GGML_UNROLL(GGML_F32_ARR)
             for (int j = 0; j < GGML_F32_ARR; j++) {
                 ax[j] = GGML_F32_VEC_LOAD(x + i + j*GGML_F32_EPR);
                 ay[j] = GGML_F32_VEC_LOAD(y + i + j*GGML_F32_EPR);
@@ -350,6 +351,7 @@ void ggml_vec_dot_f16(int n, float * GGML_RESTRICT s, size_t bs, ggml_fp16_t * G
         GGML_F16_VEC ay[GGML_F16_ARR];
 
         for (int i = 0; i < np; i += GGML_F16_STEP) {
+            GGML_UNROLL(GGML_F16_ARR)
             for (int j = 0; j < GGML_F16_ARR; j++) {
                 ax[j] = GGML_F16_VEC_LOAD(x + i + j*GGML_F16_EPR, j);
                 ay[j] = GGML_F16_VEC_LOAD(y + i + j*GGML_F16_EPR, j);
diff --git a/ggml/src/ggml-cpu/vec.h b/ggml/src/ggml-cpu/vec.h
index 5de9cb5b7e09..824d522a701b 100644
--- a/ggml/src/ggml-cpu/vec.h
+++ b/ggml/src/ggml-cpu/vec.h
@@ -284,9 +284,11 @@ inline static void ggml_vec_dot_f16_unroll(const int n, const int xs, float * GG
         GGML_F16_VEC ay[GGML_F16_ARR];
 
         for (int i = 0; i < np; i += GGML_F16_STEP) {
+            GGML_UNROLL(GGML_F16_ARR)
             for (int j = 0; j < GGML_F16_ARR; j++) {
                 ay[j] = GGML_F16_VEC_LOAD(y + i + j*GGML_F16_EPR, j);
 
+                GGML_UNROLL(GGML_VEC_DOT_UNROLL)
                 for (int k = 0; k < GGML_VEC_DOT_UNROLL; ++k) {
                     ax[j] = GGML_F16_VEC_LOAD(x[k] + i + j*GGML_F16_EPR, j);
 
@@ -414,6 +416,7 @@ inline static void ggml_vec_mad_f32(const int n, float * GGML_RESTRICT y, const
         GGML_F32_VEC ay[GGML_F32_ARR];
 
         for (int i = 0; i < np; i += GGML_F32_STEP) {
+            GGML_UNROLL(GGML_F32_ARR)
             for (int j = 0; j < GGML_F32_ARR; j++) {
                 ax[j] = GGML_F32_VEC_LOAD(x + i + j*GGML_F32_EPR);
                 ay[j] = GGML_F32_VEC_LOAD(y + i + j*GGML_F32_EPR);
@@ -562,6 +565,7 @@ inline static void ggml_vec_mad_f16(const int n, ggml_fp16_t * GGML_RESTRICT y,
     GGML_F16_VEC ay[GGML_F16_ARR];
 
     for (int i = 0; i < np; i += GGML_F16_STEP) {
+        GGML_UNROLL(GGML_F16_ARR)
         for (int j = 0; j < GGML_F16_ARR; j++) {
             ax[j] = GGML_F16_VEC_LOAD(x + i + j*GGML_F16_EPR, j);
             ay[j] = GGML_F16_VEC_LOAD(y + i + j*GGML_F16_EPR, j);
@@ -623,9 +627,11 @@ inline static void ggml_vec_mad_f32_unroll(const int n, const int xs, const int
         GGML_F32_VEC ay[GGML_F32_ARR];
 
         for (int i = 0; i < np; i += GGML_F32_STEP) {
+            GGML_UNROLL(GGML_F32_ARR)
             for (int j = 0; j < GGML_F32_ARR; j++) {
                 ay[j] = GGML_F32_VEC_LOAD(y + i + j*GGML_F32_EPR);
 
+                GGML_UNROLL(GGML_VEC_MAD_UNROLL)
                 for (int k = 0; k < GGML_VEC_MAD_UNROLL; ++k) {
                     ax[k][j] = GGML_F32_VEC_LOAD(x[k] + i + j*GGML_F32_EPR);
                     ay[j] = GGML_F32_VEC_FMA(ay[j], ax[k][j], vx[k]);
@@ -678,6 +684,7 @@ inline static void ggml_vec_mad1_f32(const int n, float * y, const float * x, co
         GGML_F32_VEC ay[GGML_F32_ARR];
 
         for (int i = 0; i < np; i += GGML_F32_STEP) {
+            GGML_UNROLL(GGML_F32_ARR)
             for (int j = 0; j < GGML_F32_ARR; j++) {
                 ay[j] = GGML_F32_VEC_LOAD(x + i + j*GGML_F32_EPR);
                 ay[j] = GGML_F32_VEC_FMA(vb, ay[j], vs);
@@ -745,6 +752,7 @@ inline static void ggml_vec_scale_f32(const int n, float * y, const float   v) {
         GGML_F32_VEC ay[GGML_F32_ARR];
 
         for (int i = 0; i < np; i += GGML_F32_STEP) {
+            GGML_UNROLL(GGML_F32_ARR)
             for (int j = 0; j < GGML_F32_ARR; j++) {
                 ay[j] = GGML_F32_VEC_LOAD(y + i + j*GGML_F32_EPR);
                 ay[j] = GGML_F32_VEC_MUL(ay[j], vx);
@@ -838,6 +846,7 @@ inline static void ggml_vec_scale_f16(const int n, ggml_fp16_t * y, const float
     GGML_F16_VEC ay[GGML_F16_ARR];
 
     for (int i = 0; i < np; i += GGML_F16_STEP) {
+        GGML_UNROLL(GGML_F16_ARR)
         for (int j = 0; j < GGML_F16_ARR; j++) {
             ay[j] = GGML_F16_VEC_LOAD(y + i + j*GGML_F16_EPR, j);
             ay[j] = GGML_F16_VEC_MUL(ay[j], vx);